© 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. 3-RES-JB
    11. 6487
    Prev
    Next
    INDEX
    Explanations

    words related to chocolates or sweet treats

    oai_token-act-pair · gpt-3.5-turbo

    terms related to chocolate and its various descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hutchinson
    -0.87
     Grayson
    -0.66
    VK
    -0.65
     Dak
    -0.64
     VIEW
    -0.62
     Shepard
    -0.61
     distance
    -0.60
     Feldman
    -0.60
     Robots
    -0.59
     WWF
    -0.59
    POSITIVE LOGITS
    ocol
    1.40
    onial
    1.26
    rador
    1.04
    ates
    1.04
    umn
    1.01
    ombo
    0.98
    atile
    0.96
    oded
    0.95
    atility
    0.95
    oria
    0.95
    Activations Density 0.007%

    No Known Activations