© 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. 1160
    Prev
    Next
    INDEX
    Explanations

    mentions of musical concerts

    oai_token-act-pair · gpt-3.5-turbo

    references to concerts

    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
     EE
    -0.68
    Continue
    -0.67
     WRITE
    -0.67
    ļ
    -0.66
    enders
    -0.63
    awed
    -0.63
     PU
    -0.63
    Accept
    -0.62
    trl
    -0.62
    ername
    -0.62
    POSITIVE LOGITS
     concert
    3.64
     Concert
    2.48
     concerts
    2.39
    concert
    1.64
     orchestra
    1.37
     rehearsal
    1.36
     opera
    1.26
     unison
    1.25
     musical
    1.24
     song
    1.21
    Activations Density 0.011%

    No Known Activations