© 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. 0-RES-JB
    11. 4095
    Prev
    Next
    INDEX
    Explanations

    financial terms and mentions of channels or shows

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of "CH" and "SCH" sequences followed by numeric values or certain context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mania
    -0.68
    fax
    -0.67
    oner
    -0.66
    Reviewer
    -0.65
    oid
    -0.65
    uri
    -0.65
     Limbaugh
    -0.64
    alus
    -0.63
    ocular
    -0.63
    annon
    -0.62
    POSITIVE LOGITS
     CH
    3.46
    CH
    2.25
     SCH
    1.57
     CHR
    1.57
    CHA
    1.50
     MIN
    1.38
    Ch
    1.38
     Ch
    1.37
     CHAR
    1.33
     PH
    1.32
    Activations Density 0.007%

    No Known Activations