© 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
    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. 23390
    Prev
    Next
    INDEX
    Explanations

    phrases related to the current state or condition of a situation

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of situations or conditions

    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
     Creed
    -0.83
     Flavoring
    -0.81
    inally
    -0.73
    enary
    -0.71
    aques
    -0.71
     swoop
    -0.69
     clasp
    -0.69
     Ezek
    -0.67
     Instruction
    -0.65
    inia
    -0.65
    POSITIVE LOGITS
     unfavorable
    1.08
     favorable
    1.04
     deteriorated
    1.02
     deterior
    0.98
     deteriorating
    0.97
     dictated
    0.93
     predictable
    0.90
     altered
    0.88
     erratic
    0.88
     favourable
    0.87
    Activations Density 0.464%

    No Known Activations