© 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. 6474
    Prev
    Next
    INDEX
    Explanations

    phrases indicating acquiring, locating, or retrieving something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "obtain" and its variations in relation to acquiring permission or access

    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
    heartedly
    -0.79
    hov
    -0.69
    psc
    -0.69
    erness
    -0.67
    kind
    -0.57
    cas
    -0.57
    evil
    -0.55
     Formation
    -0.55
     Oops
    -0.54
    bourne
    -0.54
    POSITIVE LOGITS
     permission
    1.00
     licenses
    0.88
    hold
    0.86
     authorization
    0.83
     licences
    0.82
     access
    0.80
     permits
    0.80
     signatures
    0.79
    女
    0.76
    ancial
    0.76
    Activations Density 0.065%

    No Known Activations