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. 12212
    Prev
    Next
    INDEX
    Explanations

    phrases related to positions or locations within a specific context or structure

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with the concept of "post" in various contexts

    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
    ADRA
    -0.70
     Everywhere
    -0.60
    DERR
    -0.58
    cale
    -0.58
     PsyNet
    -0.56
     Helpful
    -0.56
    ãħĭ
    -0.55
     Disabled
    -0.54
    vae
    -0.54
    Ô
    -0.52
    POSITIVE LOGITS
    iest
    0.99
    ultimate
    0.99
    liest
    0.96
    osphere
    0.93
    ieth
    0.81
    less
    0.80
    aments
    0.77
    able
    0.76
    lights
    0.74
    ivist
    0.74
    Activations Density 0.610%

    No Known Activations