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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24509
    Prev
    Next
    INDEX
    Explanations

    keywords related to investigations or legal actions by authorities

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions indicating ongoing investigations or actions being considered

    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
    Liter
    -0.77
    neath
    -0.74
    pron
    -0.72
    itans
    -0.70
    ľ
    -0.69
    lux
    -0.69
    ilt
    -0.68
    Suddenly
    -0.67
    sung
    -0.67
    Born
    -0.67
    POSITIVE LOGITS
     urged
    1.23
     vowed
    1.23
     issued
    1.14
     expects
    1.11
     ordered
    1.11
     apologized
    1.10
     intends
    1.09
     demanded
    1.07
     notified
    1.06
     announced
    1.06
    Activations Density 0.217%

    No Known Activations