© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 7811
    Prev
    Next
    INDEX
    Explanations

    descriptions of challenges or obstacles related to physical access or practical issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to obstacles and difficulties in accessing services or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oward
    -0.96
    isode
    -0.83
    Happy
    -0.81
    Changed
    -0.79
    Hit
    -0.75
    Tonight
    -0.74
    actly
    -0.74
    Action
    -0.72
    rection
    -0.70
    stasy
    -0.69
    POSITIVE LOGITS
     prohib
    1.28
     cumbers
    1.27
     manpower
    1.19
     bureaucracy
    1.12
     cumbersome
    1.10
     scarce
    1.08
     expensive
    1.08
     inexper
    1.08
     budgets
    1.07
     unreliable
    1.05
    Activations Density 0.771%

    No Known Activations