© 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. 18668
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is conveying information or providing details

    oai_token-act-pair · gpt-3.5-turbo

    statements made by spokespersons or officials

    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
    physical
    -0.65
     physical
    -0.64
    soc
    -0.64
     trivia
    -0.62
    wikipedia
    -0.61
    minus
    -0.60
    Jews
    -0.59
    PAC
    -0.59
    BOX
    -0.58
    GROUP
    -0.58
    POSITIVE LOGITS
     stern
    0.90
     QC
    0.84
    ogun
    0.79
    veland
    0.79
    terday
    0.75
    aley
    0.75
    uty
    0.69
     Appearance
    0.67
    hement
    0.67
    iewicz
    0.66
    Activations Density 0.281%

    No Known Activations