Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 17814
    Prev
    Next
    INDEX
    Explanations

    phrases indicating statements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    references to assertions or statements made about various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.68
    rag
    -0.66
     endif
    -0.66
    cheon
    -0.63
    icult
    -0.61
    activate
    -0.59
     cd
    -0.59
    othal
    -0.59
    agram
    -0.58
    nn
    -0.58
    POSITIVE LOGITS
     claims
    3.55
     Claims
    2.69
     claim
    2.48
    Claim
    2.09
    claim
    2.07
     claimed
    2.04
     allegations
    2.01
     assertions
    1.99
     Claim
    1.90
     accusations
    1.84
    Activations Density 0.019%

    No Known Activations