© 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. 7-RES-JB
    11. 8717
    Prev
    Next
    INDEX
    Explanations

    names of people and political entities

    oai_token-act-pair · gpt-3.5-turbo

    people and entities involved in discussion or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.68
     âĢİ
    -0.66
     âĢº
    -0.59
    rehens
    -0.58
    -0.55
     Cash
    -0.54
    Âł
    -0.54
    Cash
    -0.54
     <<
    -0.53
     iTunes
    -0.53
    POSITIVE LOGITS
    ucer
    0.61
     mechanics
    0.59
     itself
    0.59
    Untitled
    0.58
    gered
    0.57
     accordingly
    0.57
    '."
    0.55
     themselves
    0.55
    ilant
    0.55
     therein
    0.53
    Activations Density 1.046%

    No Known Activations