© 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. 22545
    Prev
    Next
    INDEX
    Explanations

    real estate and property-related terms

    oai_token-act-pair · gpt-3.5-turbo

    commercial real estate and urban development terms

    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
    ĻĤ
    -0.75
     Gamergate
    -0.74
     femin
    -0.69
     faked
    -0.67
    etheless
    -0.67
     faulty
    -0.65
     flawed
    -0.65
    £ı
    -0.63
    JM
    -0.63
     saliva
    -0.62
    POSITIVE LOGITS
    atorium
    1.07
     pav
    0.98
     annex
    0.98
     tents
    0.90
     plaza
    0.90
    District
    0.88
    ominium
    0.88
     downtown
    0.84
     kios
    0.82
     encamp
    0.81
    Activations Density 0.680%

    No Known Activations