© 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. 1361
    Prev
    Next
    INDEX
    Explanations

    words related to misrepresentation or misrepresentation itself

    oai_token-act-pair · gpt-3.5-turbo

    terms related to misrepresentation and its nuances

    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
    ï¸
    -0.69
    STON
    -0.69
    mith
    -0.69
    \\\\\\\\\\\\\\\\
    -0.68
    pei
    -0.64
    cius
    -0.63
    WAYS
    -0.63
     nerv
    -0.63
    vantage
    -0.62
    creen
    -0.61
    POSITIVE LOGITS
    ation
    1.62
    ations
    1.51
    ed
    1.21
    ing
    1.03
    ated
    1.01
    ating
    0.99
    eering
    0.98
    atives
    0.98
    ational
    0.97
    edly
    0.95
    Activations Density 0.036%

    No Known Activations