Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 3014
    Prev
    Next
    INDEX
    Explanations

    phrases related to the band "Grateful Dead" and specifically the member Bob Weir

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific musicians and bands, particularly the Grateful Dead and its members

    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
     Gle
    -0.74
     Lup
    -0.72
     Deg
    -0.69
     Dialogue
    -0.68
     Centauri
    -0.68
    ories
    -0.67
     Zuckerberg
    -0.67
     Chern
    -0.67
     helmets
    -0.66
     Griffith
    -0.66
    POSITIVE LOGITS
    sie
    1.06
     Grateful
    0.95
    mot
    0.95
    steen
    0.91
     Paso
    0.82
    riter
    0.82
    Reviewer
    0.81
    artney
    0.81
    akedown
    0.80
    rible
    0.80
    Activations Density 0.026%

    No Known Activations