© 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. 1-RES-JB
    11. 9509
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations or relocations

    oai_token-act-pair · gpt-3.5-turbo

    words related to locations and placement

    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
    sonian
    -0.67
    gam
    -0.58
     Answers
    -0.57
    gt
    -0.56
    win
    -0.56
     gloss
    -0.55
    gd
    -0.55
     clubhouse
    -0.55
    better
    -0.55
    arat
    -0.55
    POSITIVE LOGITS
    ocation
    1.07
    entric
    0.88
    ptives
    0.83
    ISION
    0.82
    ocations
    0.80
    aukee
    0.79
    adobe
    0.77
    ocated
    0.76
    yip
    0.76
    uador
    0.76
    Activations Density 0.016%

    No Known Activations