© 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. 6-RES-JB
    11. 11677
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical spaces or environments

    oai_token-act-pair · gpt-3.5-turbo

    references to physical spaces or areas in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blackmail
    -0.66
     ransom
    -0.65
    usted
    -0.65
    ãĥīãĥ©
    -0.64
     vengeance
    -0.63
    ochet
    -0.62
    uminati
    -0.62
     Uz
    -0.61
    ocide
    -0.60
     Canaver
    -0.59
    POSITIVE LOGITS
     spaces
    1.13
     Spaces
    0.95
    hips
    0.86
    lot
    0.84
    uits
    0.83
    adia
    0.83
     stalls
    0.83
     habitats
    0.80
    ility
    0.80
     space
    0.78
    Activations Density 0.034%

    No Known Activations