INDEX

Explanations

mentions of legal or governmental actions

oai_token-act-pair · gpt-3.5-turbo

terms related to lobbying and aggressive political strategies

oai_token-act-pair · gpt-4o-mini Triggered 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

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sacrific

-0.57

ankind

-0.56

 rook

-0.55

 Rebell

-0.55

VALUE

-0.55

 Paste

-0.55

 loneliness

-0.53

 experien

-0.53

 describ

-0.53

aph

-0.53

POSITIVE LOGITS

 subpoen

0.85

 subpoena

0.80

 Judicial

0.78

 Oversight

0.77

displayText

0.75

 congressional

0.73

 sworn

0.73

 unconstitutional

0.70

 briefed

0.67

DHS

0.67

Activations Density 1.454%

mentions of legal or governmental actions

terms related to lobbying and aggressive political strategies

No Comments

No Known Activations