INDEX

Explanations

locations or places, specifically ones related to neighborhoods or communities

oai_token-act-pair · gpt-3.5-turbo

mentions of specific geographical locations

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

anguage

-0.86

amn

-0.77

alty

-0.73

bats

-0.70

afort

-0.69

icate

-0.69

angu

-0.69

age

-0.69

podcast

-0.68

oids

-0.66

POSITIVE LOGITS

CLASSIFIED

0.88

 Grove

0.75

 Chapel

0.74

ieties

0.74

 Wick

0.70

illard

0.69

raising

0.69

adia

0.68

Spoiler

0.68

edIn

0.67

Activations Density 0.058%

locations or places, specifically ones related to neighborhoods or communities

mentions of specific geographical locations

No Comments

No Known Activations