© 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. 4-RES-JB
    11. 6727
    Prev
    Next
    INDEX
    Explanations

    phrases related to intellectual property

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intellectual property

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

    No Comments

    Negative Logits
     Mara
    -0.75
    avers
    -0.73
    borg
    -0.70
     Slay
    -0.69
     decorated
    -0.69
    rera
    -0.68
    bare
    -0.68
    iland
    -0.66
    ldon
    -0.66
    aver
    -0.66
    POSITIVE LOGITS
    ellectual
    1.02
     curiosity
    0.86
     intellectual
    0.84
     dishon
    0.82
     underpin
    0.77
     philos
    0.76
     arte
    0.75
     minds
    0.75
     enrichment
    0.74
    minded
    0.73
    Activations Density 0.011%

    No Known Activations