© 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. 9-RES-JB
    11. 13098
    Prev
    Next
    INDEX
    Explanations

    phrases related to the human back or positioned behind

    oai_token-act-pair · gpt-3.5-turbo

    references to 'back' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inational
    -0.77
    aukee
    -0.71
    entric
    -0.64
    ciation
    -0.63
    orpor
    -0.63
    ISON
    -0.62
     viz
    -0.61
    uary
    -0.61
    icity
    -0.60
     Osc
    -0.59
    POSITIVE LOGITS
    stab
    1.26
    packs
    1.21
    woods
    1.18
    side
    1.17
    seat
    1.12
    bones
    1.12
    packing
    1.11
    country
    1.10
    lash
    1.09
    GROUND
    1.07
    Activations Density 0.053%

    No Known Activations