Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 5376
    Prev
    Next
    INDEX
    Explanations

    words related to names and organizations starting with "Tr" or similar letter combinations

    oai_token-act-pair · gpt-3.5-turbo

    word patterns related to various forms of "trig" and "ul" indicating triggers and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     innocence
    -0.71
     Archdemon
    -0.65
    romeda
    -0.64
     bount
    -0.61
     mortar
    -0.58
     sunset
    -0.56
     condem
    -0.56
     prosper
    -0.55
     correctness
    -0.55
     hover
    -0.54
    POSITIVE LOGITS
    portation
    0.83
    quist
    0.82
    ħĭ
    0.76
    opers
    0.75
    bish
    0.74
    opal
    0.73
    lycer
    0.73
    oker
    0.71
    pes
    0.67
    oute
    0.67
    Activations Density 0.076%

    No Known Activations