INDEX

Explanations

the word "Sky" with varying activation levels

oai_token-act-pair · gpt-3.5-turbo

mentions of the Sky brand or its associated products and services

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

å¥³

-0.74

 ACTIONS

-0.69

Ô

-0.68

-0.66

utics

-0.66

Interstitial

-0.66

aunder

-0.65

terior

-0.63

aphael

-0.63

POSITIVE LOGITS

Sky

1.02

hawk

0.99

fax

0.94

bone

0.93

lake

0.92

Eye

0.88

eus

0.86

 Trading

0.85

Sky

0.84

link

0.84

Activations Density 0.007%

the word "Sky" with varying activation levels

mentions of the Sky brand or its associated products and services

No Comments

No Known Activations