INDEX

Explanations

the word "lie" and related forms

oai_token-act-pair · gpt-3.5-turbo

instances of the word "lie" and its variations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aldi

-0.81

ugal

-0.76

orsi

-0.71

joining

-0.68

iles

-0.66

ISO

-0.66

FN

-0.65

allows

-0.65

 nomine

-0.64

ilation

-0.63

POSITIVE LOGITS

 detector

1.05

uten

0.97

utenant

0.82

bling

0.79

 unfocusedRange

0.79

ge

0.79

lie

0.77

chet

0.76

ulent

0.76

 detectors

0.74

Activations Density 0.026%

the word "lie" and related forms

instances of the word "lie" and its variations

No Comments

No Known Activations