INDEX

Explanations

obscured words containing the letters "ob" in a sentence

oai_token-act-pair · gpt-3.5-turbo

references to "obituaries" or related content

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

 guiActiveUnfocused

-1.01

EngineDebug

-0.99

agne

-0.83

anwhile

-0.80

 Prosper

-0.75

 Carlson

-0.73

gas

-0.73

terday

-0.72

 Michaels

-0.70

 Idle

-0.68

POSITIVE LOGITS

lique

1.53

livion

1.30

eyed

1.15

structed

1.11

nox

1.07

sole

1.04

amacare

1.03

olescent

1.03

tains

1.03

ject

1.01

Activations Density 0.013%

obscured words containing the letters "ob" in a sentence

references to "obituaries" or related content

No Comments

No Known Activations