© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19738
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experience or inner thoughts

    oai_token-act-pair · gpt-3.5-turbo

    first-person singular pronouns indicating personal experiences or feelings

    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
    INGTON
    -0.61
     Kelvin
    -0.58
     Philipp
    -0.58
     Shelby
    -0.55
     Vald
    -0.54
     Alternative
    -0.54
     Ep
    -0.53
     Jarrett
    -0.53
     Aberdeen
    -0.53
    minster
    -0.53
    POSITIVE LOGITS
    'm
    1.41
    've
    1.30
     suppose
    1.20
    'll
    1.19
    'd
    1.08
     guess
    1.01
    ggy
    0.96
    rises
    0.92
    RL
    0.89
    ANA
    0.89
    Activations Density 0.388%

    No Known Activations