© 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. 9-RES-JB
    6. 1739
    Prev
    Next
    INDEX
    Explanations

    phrases related to computer instructions or coding

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to software installation and device setup

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dope
    -0.81
     stunt
    -0.77
    NPR
    -0.76
     joke
    -0.71
     funeral
    -0.70
     hurt
    -0.67
     helicop
    -0.66
     feud
    -0.66
     riot
    -0.65
     crem
    -0.65
    POSITIVE LOGITS
     Browse
    1.13
    select
    1.00
    config
    0.97
     Enable
    0.97
     Config
    0.96
    settings
    0.95
     Select
    0.94
     Settings
    0.94
    Brow
    0.92
     Preferences
    0.91
    Activations Density 0.185%

    No Known Activations