© 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. 2-RES-JB
    11. 4452
    Prev
    Next
    INDEX
    Explanations

    keywords related to reaching the highest point or level of something

    oai_token-act-pair · gpt-3.5-turbo

    references to trends and changes in levels or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aer
    -0.77
    ire
    -0.75
    esan
    -0.73
    ledge
    -0.71
    appro
    -0.70
    ĪĴ
    -0.69
    erie
    -0.68
    eely
    -0.67
    dain
    -0.67
    alle
    -0.66
    POSITIVE LOGITS
     peaked
    0.91
     peaks
    0.82
     spike
    0.72
     ceilings
    0.68
     spikes
    0.67
    uates
    0.67
    ãĤ¤ãĥĪ
    0.67
     peak
    0.65
    ratulations
    0.65
     curfew
    0.64
    Activations Density 0.006%

    No Known Activations