INDEX

Explanations

words related to moral or ethical transgressions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "foul" and related contexts

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

Downloadha

-0.75

UNCH

-0.72

_>

-0.72

ocobo

-0.71

amaru

-0.71

edia

-0.70

 Puzzles

-0.67

hare

-0.67

igslist

-0.66

akeru

-0.64

POSITIVE LOGITS

cery

0.88

terness

0.85

 smelling

0.78

sie

0.73

mson

0.70

unction

0.70

wyn

0.69

ster

0.69

mire

0.68

 foul

0.68

Activations Density 0.013%

words related to moral or ethical transgressions

instances of the word "foul" and related contexts

No Comments

No Known Activations