© 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. 2-RES-JB
    11. 3888
    Prev
    Next
    INDEX
    Explanations

    references to sequels or subsequent parts of a series

    oai_token-act-pair · gpt-3.5-turbo

    references to installments in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eric
    -0.78
    gans
    -0.72
    aiman
    -0.71
    yer
    -0.70
    bara
    -0.69
    mouth
    -0.69
    ello
    -0.69
    eating
    -0.68
    acia
    -0.67
    idi
    -0.65
    POSITIVE LOGITS
     installment
    1.24
     installments
    1.08
    itial
    0.74
    ĸļ
    0.70
     dues
    0.69
     thereof
    0.69
    Charges
    0.68
    ription
    0.68
     Tactics
    0.68
     iteration
    0.67
    Activations Density 0.007%

    No Known Activations