© 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. 913
    Prev
    Next
    INDEX
    Explanations

    words related to lack of understanding or knowledge, especially in relation to various situations or information

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases related to lack of knowledge or understanding

    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
     Ammo
    -0.76
     Shock
    -0.66
     ATF
    -0.64
     Flowers
    -0.63
     Stead
    -0.63
     DPS
    -0.61
     Brill
    -0.61
     Naval
    -0.59
     ALP
    -0.59
     Faust
    -0.57
    POSITIVE LOGITS
     deem
    0.76
    968
    0.75
    xf
    0.72
     otherwise
    0.71
    self
    0.71
    rina
    0.70
    ãĥ¯ãĥ³
    0.69
    cest
    0.69
    xa
    0.68
    entials
    0.67
    Activations Density 0.194%

    No Known Activations