© 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. 7-RES-JB
    11. 13341
    Prev
    Next
    INDEX
    Explanations

    words related to granting or providing access to resources or content

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to access to information or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieu
    -0.69
    çĶ°
    -0.65
    VERT
    -0.64
     Rats
    -0.63
     Cowboy
    -0.60
    addle
    -0.60
    ention
    -0.58
     heed
    -0.57
    stad
    -0.57
     Pwr
    -0.56
    POSITIVE LOGITS
     resources
    0.80
     trove
    0.79
     secrets
    0.77
     premises
    0.76
     bloodstream
    0.74
     encrypted
    0.72
     databases
    0.71
     uninterrupted
    0.71
     facilities
    0.70
     archives
    0.70
    Activations Density 0.263%

    No Known Activations