© 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. 953
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is being done for the benefit or interest of someone or something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the importance of context or reasoning behind actions and decisions

    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
    sbm
    -0.76
    ibr
    -0.65
    ombs
    -0.60
    interstitial
    -0.60
    zx
    -0.59
    car
    -0.58
     corrid
    -0.58
    ve
    -0.58
    ß
    -0.56
    taboola
    -0.56
    POSITIVE LOGITS
     sake
    1.01
    lihood
    0.82
    resy
    0.79
    istical
    0.79
    atsu
    0.71
    ¬¼
    0.70
    uming
    0.70
     consistency
    0.69
    )].
    0.68
    olicy
    0.67
    Activations Density 0.020%

    No Known Activations