© 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. 11-RES-JB
    11. 21383
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting origins or historical background

    oai_token-act-pair · gpt-3.5-turbo

    statements or claims about events or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    displayText
    -0.88
    Recommend
    -0.84
    etting
    -0.84
    HQ
    -0.82
     rollout
    -0.80
     Accountability
    -0.80
    Media
    -0.79
    Policy
    -0.79
    HCR
    -0.78
    ensor
    -0.77
    POSITIVE LOGITS
     witches
    1.27
     sailors
    1.26
     monks
    1.20
     archaeologists
    1.20
     poets
    1.15
     rabbits
    1.15
     pilgrims
    1.12
     pige
    1.12
     mankind
    1.11
     explorers
    1.10
    Activations Density 0.476%

    No Known Activations