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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 18717
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is expressing a strong personal belief or certainty about something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of conviction or strong belief

    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
    umbn
    -0.68
     Rover
    -0.65
     spills
    -0.64
    pmwiki
    -0.64
     Occupations
    -0.64
     Cheong
    -0.63
     Organisation
    -0.62
    ateral
    -0.62
    eworthy
    -0.62
     Miko
    -0.60
    POSITIVE LOGITS
     convinced
    0.98
    phas
    0.75
     persuaded
    0.75
     convince
    0.75
    tale
    0.74
    -+-+
    0.72
    rican
    0.72
    rified
    0.68
    rix
    0.67
    Sense
    0.67
    Activations Density 0.015%

    No Known Activations