INDEX

Explanations

phrases indicating permission or capability

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "allow for."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Originally

-0.76

oller

-0.70

edin

-0.70

mare

-0.70

soever

-0.69

 Notting

-0.66

Nation

-0.66

Champ

-0.65

bug

-0.64

CLOSE

-0.64

POSITIVE LOGITS

bidden

0.96

geries

0.95

rocal

0.85

gery

0.84

gotten

0.82

WARD

0.78

 conting

0.73

 redress

0.72

 institutional

0.71

 unrestricted

0.71

Activations Density 0.135%

phrases indicating permission or capability

occurrences of the phrase "allow for."

No Comments

No Known Activations