© 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. 8526
    Prev
    Next
    INDEX
    Explanations

    chemical substances or compounds in a gaseous state

    oai_token-act-pair · gpt-3.5-turbo

    words associated with vapor, ownership, and significant achievements

    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
     grip
    -0.73
    theless
    -0.71
     transmission
    -0.67
    REDACTED
    -0.65
    backer
    -0.62
     snail
    -0.62
     draw
    -0.60
     Behavioral
    -0.60
     Commonwealth
    -0.59
     Danish
    -0.59
    POSITIVE LOGITS
    orial
    1.41
    ors
    1.39
    ored
    1.30
    ours
    1.25
    orship
    1.21
    ures
    1.16
    our
    1.15
    eless
    1.14
    oral
    1.12
    oric
    1.11
    Activations Density 0.075%

    No Known Activations