© 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. 4-RES-JB
    11. 13214
    Prev
    Next
    INDEX
    Explanations

    words related to confirming information or news

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "confirmed."

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

    No Comments

    Negative Logits
     ILCS
    -0.98
    pen
    -0.80
    ï¸
    -0.77
    DragonMagazine
    -0.74
    onew
    -0.74
    brance
    -0.73
    fore
    -0.72
    benefit
    -0.72
    NetMessage
    -0.71
    pmwiki
    -0.70
    POSITIVE LOGITS
    irmation
    0.85
    irms
    0.82
     confirmed
    0.80
     confirms
    0.78
    atory
    0.75
     confirming
    0.74
    irmed
    0.73
    ariat
    0.72
     confirmation
    0.72
    ations
    0.72
    Activations Density 0.026%

    No Known Activations