INDEX

Explanations

mentions of rules or regulations within various contexts

oai_token-act-pair · gpt-3.5-turbo

references to regulations and rules

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ience

-0.88

 experien

-0.79

itate

-0.75

apest

-0.71

aged

-0.70

issance

-0.67

 Bras

-0.66

ingly

-0.65

 spect

-0.64

 Gree

-0.63

POSITIVE LOGITS

 governing

1.08

breakers

0.99

book

0.97

books

0.93

 lawy

0.92

 Enforcement

0.91

breaker

0.89

heet

0.89

 prohibiting

0.87

 violations

0.86

Activations Density 0.028%

mentions of rules or regulations within various contexts

references to regulations and rules

No Comments

No Known Activations