© 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. 4-RES-JB
    11. 13164
    Prev
    Next
    INDEX
    Explanations

    words related to technical details and processes, such as precision, terminations, and machining

    oai_token-act-pair · gpt-3.5-turbo

    financial terms and references to price, value, and cost

    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
    ONEY
    -0.57
    KEY
    -0.50
     Wilde
    -0.44
    aida
    -0.43
     Kills
    -0.42
     Rosenthal
    -0.42
    inea
    -0.41
    skill
    -0.41
     Aus
    -0.41
     nominate
    -0.41
    POSITIVE LOGITS
    tenance
    0.75
    terday
    0.68
    etheless
    0.67
    osterone
    0.64
    quartered
    0.64
    lihood
    0.62
    ruction
    0.59
    llor
    0.57
    roying
    0.52
    mosp
    0.51
    Activations Density 0.496%

    No Known Activations