© 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. 8-RES-JB
    11. 18593
    Prev
    Next
    INDEX
    Explanations

    locations, focusing specifically on cities and states

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rapport
    -0.65
    ãĤ¯
    -0.63
     positives
    -0.62
     Moment
    -0.62
     plank
    -0.59
    erity
    -0.58
     boards
    -0.58
     latent
    -0.58
    =/
    -0.57
    ISA
    -0.57
    POSITIVE LOGITS
     Springs
    0.91
     suburb
    0.83
     Heights
    0.82
     countryside
    0.81
    atche
    0.79
     Township
    0.79
    ensis
    0.76
     Junction
    0.75
     City
    0.72
     township
    0.71
    Activations Density 0.316%

    No Known Activations