INDEX

Explanations

verbs or phrases related to pursuit or tracking someone/something down

oai_token-act-pair · gpt-3.5-turbo

phrases related to tracking and arresting individuals

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

jab

-0.78

Cola

-0.77

 pane

-0.76

enum

-0.75

wcs

-0.72

interstitial

-0.71

paren

-0.68

placed

-0.68

 palate

-0.65

uph

-0.65

POSITIVE LOGITS

 informants

0.90

 burgl

0.86

 suspects

0.85

 Detective

0.79

 sightings

0.79

 UFOs

0.78

 Victims

0.78

 robbers

0.77

 RCMP

0.77

 terrorists

0.75

Activations Density 0.163%

verbs or phrases related to pursuit or tracking someone/something down

phrases related to tracking and arresting individuals

No Comments

No Known Activations