Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23636
    Prev
    Next
    INDEX
    Explanations

    Roman numerals representing the number 3 in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the Roman numeral "III" and related numerical designations

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

    No Comments

    Negative Logits
    sters
    -0.77
    bear
    -0.74
    pal
    -0.73
    feed
    -0.72
    arching
    -0.72
    д
    -0.71
    poll
    -0.71
    bel
    -0.71
    clock
    -0.69
    machine
    -0.69
    POSITIVE LOGITS
    rd
    1.07
    III
    1.03
    II
    0.98
     III
    0.87
    RD
    0.82
    RF
    0.77
    HM
    0.76
     Jinping
    0.74
    DS
    0.73
    HF
    0.72
    Activations Density 0.007%

    No Known Activations