© 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. 3050
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating location

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "next to" and its variations indicating spatial relationships

    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
    amara
    -0.70
    ebus
    -0.69
    izens
    -0.69
    OY
    -0.68
    nation
    -0.68
    anke
    -0.66
    é¾
    -0.66
    arling
    -0.66
    ãĤ¢ãĥ«
    -0.66
    chell
    -0.64
    POSITIVE LOGITS
     hers
    0.88
     ours
    0.76
    rium
    0.74
     Interstate
    0.71
     theirs
    0.68
     him
    0.68
     each
    0.67
     mine
    0.66
     Marilyn
    0.66
     nowhere
    0.66
    Activations Density 0.068%

    No Known Activations