INDEX

Explanations

places or locations

oai_token-act-pair · gpt-3.5-turbo

references to various locations or places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

DOS

-0.75

FIN

-0.74

quel

-0.74

ivation

-0.72

arb

-0.71

atorium

-0.70

CHAT

-0.70

XT

-0.69

UTH

-0.68

Prin

-0.68

POSITIVE LOGITS

hare

0.97

 locations

0.97

 frequ

0.96

chool

0.86

pots

0.83

 malls

0.81

 airports

0.81

abouts

0.80

hips

0.80

 landmarks

0.79

Activations Density 0.121%

places or locations

references to various locations or places

No Comments

No Known Activations