© 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. 0-RES-JB
    11. 4119
    Prev
    Next
    INDEX
    Explanations

    phrases related to positive feedback or approval

    oai_token-act-pair · gpt-3.5-turbo

    words related to puffs and soft, airy textures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĵĺ
    -0.85
    chn
    -0.68
    NK
    -0.68
    RC
    -0.67
    nl
    -0.66
    nit
    -0.66
    orge
    -0.64
    con
    -0.64
    á½
    -0.64
    IPS
    -0.63
    POSITIVE LOGITS
    eday
    0.69
    */(
    0.67
    ©¶æ
    0.66
    edia
    0.66
    roy
    0.65
    endas
    0.64
     vouchers
    0.63
    ĸļ
    0.63
    artments
    0.63
    akeru
    0.62
    Activations Density 0.000%

    No Known Activations