© 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. 1-RES-JB
    11. 18770
    Prev
    Next
    INDEX
    Explanations

    Instances where manual actions are involved or required

    oai_token-act-pair · gpt-3.5-turbo

    references to manual actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kerry
    -0.78
    riots
    -0.71
    dar
    -0.70
    soon
    -0.68
     McGr
    -0.68
    ĸļ
    -0.66
    ends
    -0.66
    Sean
    -0.66
    our
    -0.65
    Magikarp
    -0.65
    POSITIVE LOGITS
     manually
    1.12
     exting
    0.97
     encount
    0.96
    ©¶æ
    0.95
     destro
    0.93
     eleph
    0.92
     calibr
    0.86
     earthqu
    0.85
     withd
    0.85
     bleed
    0.85
    Activations Density 0.007%

    No Known Activations