© 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. 6017
    Prev
    Next
    INDEX
    Explanations

    phrases related to beliefs or faith

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing belief or conviction

    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
    killed
    -0.79
    soever
    -0.69
    HM
    -0.64
    lot
    -0.64
    hai
    -0.63
    BUS
    -0.63
    CVE
    -0.61
    SourceFile
    -0.60
    emo
    -0.59
    loo
    -0.59
    POSITIVE LOGITS
    clus
    1.29
    clusions
    1.04
    clusively
    0.91
    ordinate
    0.89
     accordance
    0.89
    effic
    0.88
    animate
    0.87
     regards
    0.85
     relation
    0.84
    escap
    0.82
    Activations Density 0.078%

    No Known Activations