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

    Neuronpedia

    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. 1-RES-JB
    11. 24263
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or processes, in particular, those associated with causing some form of change

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of 'entitlement'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    姫
    -0.88
     STAR
    -0.74
     Accountability
    -0.72
     Jenner
    -0.72
    士
    -0.70
    pmwiki
    -0.69
     Bleach
    -0.68
     Responsibility
    -0.65
     Negative
    -0.65
    é¾įåĸļ士
    -0.63
    POSITIVE LOGITS
     ent
    1.07
    rave
    0.99
    eering
    0.87
    inence
    0.86
    cyclopedia
    0.86
    igent
    0.85
    ropy
    0.85
    ourage
    0.84
    renched
    0.83
    urous
    0.81
    Activations Density 0.004%

    No Known Activations