© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 13604
    Prev
    Next
    INDEX
    Explanations

    horizontal concepts or features

    oai_token-act-pair · gpt-3.5-turbo

    terms related to horizontal alignment or positioning

    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
    rd
    -1.15
    ussion
    -0.89
    alez
    -0.88
    olia
    -0.84
    icles
    -0.80
    obal
    -0.79
    ollo
    -0.78
    iasco
    -0.76
    hetti
    -0.76
    uld
    -0.74
    POSITIVE LOGITS
    UGH
    0.69
    entary
    0.66
     thirds
    0.65
    soever
    0.63
    shock
    0.63
     flats
    0.61
     Huckabee
    0.61
    192
    0.60
     Qi
    0.58
    âĶĢ
    0.58
    Activations Density 0.045%

    No Known Activations