© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 23591
    Prev
    Next
    INDEX
    Explanations

    references to barber shops

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hop" in various contexts related to hip-hop culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.80
    MRI
    -0.68
    INE
    -0.66
    Reviewer
    -0.64
    UCT
    -0.64
     wolves
    -0.63
     Bath
    -0.62
    evil
    -0.62
    VID
    -0.59
    DIT
    -0.59
    POSITIVE LOGITS
    hop
    1.62
    efully
    1.31
    eful
    1.19
    hops
    1.18
    Hop
    1.10
    daq
    0.86
    alog
    0.86
    yright
    0.84
     hop
    0.83
    otle
    0.82
    Activations Density 0.007%

    No Known Activations