© 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. 18544
    Prev
    Next
    INDEX
    Explanations

    phrases related to numerical figures and measurements

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and metrics related to statistics or data

    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
    .''
    -0.59
    .''.
    -0.56
    .'"
    -0.56
    ]."
    -0.55
    ."
    -0.55
    )."
    -0.50
    .).
    -0.49
    .)
    -0.47
     spokeswoman
    -0.46
    .�
    -0.46
    POSITIVE LOGITS
     Whilst
    0.65
    ³³³
    0.58
     whilst
    0.54
    Firstly
    0.53
     misunder
    0.51
     organise
    0.50
    ³³³³³³³³
    0.50
     Firstly
    0.50
    orkshire
    0.49
    terday
    0.48
    Activations Density 3.179%

    No Known Activations