© 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. 8-RES-JB
    11. 2772
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific topics or subjects mentioned in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atel
    -0.90
    wcsstore
    -0.75
    USB
    -0.74
    BUS
    -0.73
    #$
    -0.73
    daq
    -0.70
    tre
    -0.70
    APD
    -0.69
    [_
    -0.68
    Position
    -0.68
    POSITIVE LOGITS
    effic
    1.13
     lieu
    1.09
     general
    1.08
    efficiency
    1.00
     nutshell
    0.98
     relation
    0.98
     accordance
    0.97
     America
    0.92
    clusions
    0.90
    clus
    0.90
    Activations Density 0.299%

    No Known Activations