INDEX

Explanations

statements containing the word "lies"

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the word "lies."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ktop

-0.89

phan

-0.66

chid

-0.63

 Dynam

-0.63

EMP

-0.61

Jackson

-0.60

azz

-0.59

iop

-0.59

 Recommended

-0.58

NB

-0.58

POSITIVE LOGITS

 lies

3.95

lie

2.66

 Lies

2.12

 lying

1.78

 falsehood

1.74

 rests

1.53

 lied

1.52

 resides

1.50

 liar

1.35

 deceit

1.30

Activations Density 0.009%

statements containing the word "lies"

repeated mentions of the word "lies."

No Comments

No Known Activations