INDEX

Explanations

words related to darkness or depth

oai_token-act-pair · gpt-3.5-turbo

terms related to darkness and deep emotional themes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

berman

-0.88

DOM

-0.84

icip

-0.84

hers

-0.81

eer

-0.81

UTERS

-0.80

 WATCHED

-0.80

cription

-0.74

Page

-0.73

PET

-0.73

POSITIVE LOGITS

 darkest

1.11

 violet

1.09

 darker

1.01

 grey

0.99

 tones

0.94

 dark

0.93

 depths

0.91

 tint

0.91

 brown

0.91

hue

0.88

Activations Density 0.011%

words related to darkness or depth

terms related to darkness and deep emotional themes

No Comments

No Known Activations