© 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. 2-RES-JB
    11. 24218
    Prev
    Next
    INDEX
    Explanations

    the concept of freedom

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to freedom and expression

    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
    ergy
    -0.85
    IFIC
    -0.77
    amac
    -0.74
    itant
    -0.72
     Dynasty
    -0.69
    assium
    -0.67
    IENT
    -0.66
    liam
    -0.66
    recorded
    -0.64
    athan
    -0.63
    POSITIVE LOGITS
     freedom
    1.06
     roam
    0.98
    freedom
    0.96
     freedoms
    0.96
    bies
    0.92
     captives
    0.82
     prisoners
    0.78
     unrestricted
    0.77
     prisoner
    0.76
     communism
    0.74
    Activations Density 0.021%

    No Known Activations