INDEX

Explanations

words related to cities or neighborhoods

oai_token-act-pair · gpt-3.5-turbo

terms related to locations or settings, especially ones that emphasize urban or communal aspects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

NetMessage

-0.89

å£«

-0.86

 Flavoring

-0.82

Reviewer

-0.78

Magikarp

-0.77

interstitial

-0.76

CVE

-0.75

UTION

-0.75

 Marketable

-0.75

TPPStreamerBot

-0.75

POSITIVE LOGITS

reme

1.14

rix

1.11

oday

1.09

ypes

1.02

hetically

1.00

ype

0.98

ension

0.96

arist

0.92

rano

0.91

ainment

0.91

Activations Density 0.023%

words related to cities or neighborhoods

terms related to locations or settings, especially ones that emphasize urban or communal aspects

No Comments

No Known Activations