© 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. 0-RES-JB
    11. 16470
    Prev
    Next
    INDEX
    Explanations

    mentions of hackers

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spur
    -0.82
     Medina
    -0.76
     Relative
    -0.74
     Towns
    -0.74
    addle
    -0.73
    Ref
    -0.72
     Sadd
    -0.71
    Duration
    -0.71
     Bris
    -0.68
     NH
    -0.68
    POSITIVE LOGITS
     hackers
    3.66
     hacker
    3.30
     hacking
    2.81
     hack
    2.25
     hacked
    2.07
     hacks
    2.04
     cyber
    1.98
     Hacker
    1.96
     cybersecurity
    1.89
     Hack
    1.84
    Activations Density 0.019%

    No Known Activations