© 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. 15139
    Prev
    Next
    INDEX
    Explanations

    words related to physical barriers or security measures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to barriers and security measures

    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
    apest
    -0.79
    incarn
    -0.77
    resents
    -0.74
    20439
    -0.72
    anne
    -0.68
    ospels
    -0.65
    eneg
    -0.65
    alky
    -0.65
    ":"/
    -0.65
    Tax
    -0.63
    POSITIVE LOGITS
     perimeter
    1.17
     checkpoints
    1.16
     barric
    1.14
     fence
    1.12
     fences
    1.11
     guarding
    1.03
     fencing
    1.02
     patrols
    1.01
     erected
    1.00
     lockdown
    0.98
    Activations Density 0.240%

    No Known Activations