INDEX

Explanations

phrases related to legal or policy aspects of business practices

oai_token-act-pair · gpt-3.5-turbo

occurrences of refusal or denial related to service or rights based on certain criteria

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

âĹ¼

-0.76

terness

-0.72

ãĤ´ãĥ³

-0.71

cffffcc

-0.71

Mom

-0.70

itsch

-0.69

 luckily

-0.69

isSpecialOrderable

-0.68

Ire

-0.68

çĶ°

-0.66

POSITIVE LOGITS

 certain

0.93

 discriminatory

0.79

 licenses

0.75

 lawfully

0.74

 their

0.73

enance

0.72

 discretionary

0.70

 objectionable

0.69

 harmful

0.69

 arbitrary

0.68

Activations Density 0.417%

phrases related to legal or policy aspects of business practices

occurrences of refusal or denial related to service or rights based on certain criteria

No Comments

No Known Activations