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. 8-RES-JB
    6. 9185
    Prev
    Next
    INDEX
    Explanations

    actions or intentions that are followed by attempts to do something

    oai_token-act-pair · gpt-3.5-turbo

    actions related to attempts or efforts to do something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hander
    -0.80
    workers
    -0.77
    eyes
    -0.76
    houses
    -0.75
    spr
    -0.75
    era
    -0.68
    room
    -0.68
    lined
    -0.68
    father
    -0.67
    front
    -0.67
    POSITIVE LOGITS
     unsuccessfully
    1.12
     resusc
    0.83
     suicide
    0.79
    URES
    0.78
    URE
    0.77
    llor
    0.76
    Attempts
    0.74
     emulate
    0.74
     relocation
    0.71
    ossibility
    0.70
    Activations Density 0.041%

    No Known Activations