© 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. 6-RES-JB
    11. 7065
    Prev
    Next
    INDEX
    Explanations

    frequent references to the term "joy."

    oai_token-act-pair · gpt-3.5-turbo

    expressions and concepts related to joy and happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pta
    -0.72
    iban
    -0.66
     conflic
    -0.63
     helicop
    -0.61
     backdoor
    -0.60
     Rhod
    -0.60
     comma
    -0.59
     penal
    -0.58
    chnology
    -0.58
     stockp
    -0.57
    POSITIVE LOGITS
    sticks
    1.41
    fully
    1.32
    ously
    1.25
    ous
    1.20
    joy
    1.10
    ride
    1.06
    fulness
    0.98
    iously
    0.98
    son
    0.95
    rous
    0.94
    Activations Density 0.018%

    No Known Activations