© 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. 6172
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions and processes

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to processing, storing, and delivering various forms of content or materials

    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
    RET
    -0.74
    burgh
    -0.64
    ECK
    -0.64
    OUR
    -0.60
    HY
    -0.60
    othy
    -0.60
    ERC
    -0.59
    ouf
    -0.59
    Forest
    -0.58
    entity
    -0.58
    POSITIVE LOGITS
     abroad
    0.99
     elsewhere
    0.86
     therein
    0.83
     outside
    0.81
     thereto
    0.80
     outdoors
    0.78
     by
    0.77
     herein
    0.76
     pursuant
    0.76
    abouts
    0.76
    Activations Density 0.212%

    No Known Activations