© 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. 3-RES-JB
    11. 12002
    Prev
    Next
    INDEX
    Explanations

    expressions related to accomplishment or strong positive sentiments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "rem" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gerald
    -0.76
     Labrador
    -0.67
     Cue
    -0.66
     behold
    -0.65
     McCabe
    -0.63
     McF
    -0.63
     Flan
    -0.62
     Hath
    -0.62
     Ack
    -0.61
    gio
    -0.61
    POSITIVE LOGITS
    nants
    1.20
    nant
    1.10
    ovable
    1.09
    arkable
    1.02
    ploy
    1.02
    oval
    0.97
    antle
    0.96
    akers
    0.95
    phas
    0.95
    oved
    0.95
    Activations Density 0.009%

    No Known Activations