© 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. 11577
    Prev
    Next
    INDEX
    Explanations

    phrases related to unity and support

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "the."

    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
     raised
    -0.65
     reverse
    -0.59
     dangerously
    -0.58
     receipts
    -0.58
     domestically
    -0.57
     DPRK
    -0.57
     downtime
    -0.57
     ob
    -0.56
     slash
    -0.56
     realm
    -0.56
    POSITIVE LOGITS
    te
    4.47
    tes
    2.69
    TE
    1.98
    Te
    1.85
    ten
    1.53
    tec
    1.51
    ts
    1.47
    ting
    1.46
    ty
    1.45
    ta
    1.44
    Activations Density 0.021%

    No Known Activations