INDEX

Explanations

words related to rules or regulations

oai_token-act-pair · gpt-3.5-turbo

mentions of regulations and related rules or guidelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

minster

-0.90

ience

-0.85

ocent

-0.76

strap

-0.74

nie

-0.73

joy

-0.72

stocks

-0.72

Neh

-0.72

oscopic

-0.69

ãĥ¤

-0.69

POSITIVE LOGITS

 governing

1.17

 promulg

1.13

 imposed

1.06

 permitting

1.03

 regulating

1.00

 enforcement

0.93

 prohibiting

0.93

 restricting

0.91

 Enforcement

0.91

 enforced

0.90

Activations Density 0.055%

words related to rules or regulations

mentions of regulations and related rules or guidelines

No Comments

No Known Activations