© 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. 8-RES-JB
    11. 15099
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs related to freedom or liberty

    oai_token-act-pair · gpt-3.5-turbo

    words indicating freedom or the ability to act without restriction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IONS
    -0.69
    IRE
    -0.67
    ATIONAL
    -0.65
    EMENT
    -0.64
    ilege
    -0.59
    idency
    -0.58
    ATIONS
    -0.58
    raints
    -0.58
    ANCE
    -0.57
    ruction
    -0.57
    POSITIVE LOGITS
     enough
    1.15
    founded
    0.99
     asleep
    0.95
    enough
    0.89
    wired
    0.88
    ened
    0.83
    handedly
    0.82
    sighted
    0.81
     Enough
    0.78
    fed
    0.78
    Activations Density 0.281%

    No Known Activations