© 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. 13456
    Prev
    Next
    INDEX
    Explanations

    phrases related to statements made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    segments of text related to legal or regulatory issues

    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
    heit
    -0.78
     contempl
    -0.77
     adolesc
    -0.76
    kees
    -0.76
     favorably
    -0.74
     Saiyan
    -0.70
     undermin
    -0.69
     pursued
    -0.68
     composing
    -0.68
     attent
    -0.68
    POSITIVE LOGITS
    CBC
    1.07
    READ
    1.00
     Scotia
    0.90
    Hal
    0.89
    Owner
    0.87
    Ott
    0.87
     CBC
    0.86
    Terry
    0.84
    Companies
    0.83
    Coun
    0.83
    Activations Density 0.323%

    No Known Activations