© 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. 2757
    Prev
    Next
    INDEX
    Explanations

    phrases related to plans or intentions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future possibilities or plans

    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
     SHARES
    -0.69
    OHN
    -0.68
    76561
    -0.67
    assador
    -0.63
    ARDIS
    -0.63
     Flavoring
    -0.62
    rand
    -0.61
     Supports
    -0.61
     unwittingly
    -0.61
    iscons
    -0.61
    POSITIVE LOGITS
     forefront
    0.96
     realm
    0.94
     hands
    0.83
     simplest
    0.82
     scope
    0.81
     ballpark
    0.80
     drawer
    0.79
     minds
    0.78
     vein
    0.76
     envelope
    0.75
    Activations Density 0.302%

    No Known Activations