© 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. 1-RES-JB
    11. 20125
    Prev
    Next
    INDEX
    Explanations

    terms related to assumptions being made

    oai_token-act-pair · gpt-3.5-turbo

    references to assumptions

    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
    Interstitial
    -0.81
     deed
    -0.69
    hern
    -0.68
    HCR
    -0.66
    amen
    -0.65
    sung
    -0.65
    iferation
    -0.64
    paying
    -0.64
    ching
    -0.64
    aska
    -0.63
    POSITIVE LOGITS
     assumptions
    1.32
     assumption
    1.16
     assum
    0.91
     assumes
    0.81
     princ
    0.81
     biases
    0.79
     underpin
    0.78
     assume
    0.76
     guesses
    0.74
     mistakes
    0.74
    Activations Density 0.011%

    No Known Activations