© 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. 2-RES-JB
    11. 19451
    Prev
    Next
    INDEX
    Explanations

    words related to computer security software and terms that may be hexadecimal code

    oai_token-act-pair · gpt-3.5-turbo

    words associated with animals and specific locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.90
    cloth
    -0.79
    UCT
    -0.76
    manship
    -0.75
    Scar
    -0.74
    holders
    -0.71
    busters
    -0.70
    Haunted
    -0.69
    åŃIJ
    -0.67
    IDA
    -0.67
    POSITIVE LOGITS
    ayan
    0.95
    imal
    0.92
    arya
    0.84
    ogy
    0.84
    ysis
    0.82
    arial
    0.82
    arius
    0.79
     Nadu
    0.78
    ORPG
    0.78
     Pradesh
    0.76
    Activations Density 0.016%

    No Known Activations