© 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. 3735
    Prev
    Next
    INDEX
    Explanations

    CSS and JavaScript code snippets related to the positioning of elements on a web page

    oai_token-act-pair · gpt-3.5-turbo

    specific types of location-related terminology and structure in written content

    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
    illet
    -0.81
    axe
    -0.79
    merce
    -0.75
    reau
    -0.72
    Brother
    -0.68
    sels
    -0.66
    ruary
    -0.66
    errilla
    -0.66
    onest
    -0.65
    arty
    -0.65
    POSITIVE LOGITS
    limits
    0.76
     Viper
    0.72
     deprivation
    0.71
     SCP
    0.71
     heightened
    0.68
     disturbances
    0.67
     isot
    0.67
     confidentiality
    0.66
     disturbance
    0.65
     deteriorated
    0.64
    Activations Density 0.639%

    No Known Activations