INDEX

Explanations

words related to causes and effects

oai_token-act-pair · gpt-3.5-turbo

relationships between symptoms and underlying causes or conditions in societal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ntax

-0.65

asions

-0.65

 skulls

-0.64

 diction

-0.64

intend

-0.63

fax

-0.61

 Owens

-0.61

ells

-0.59

 axes

-0.59

ancies

-0.58

POSITIVE LOGITS

wart

0.80

itect

0.77

 testament

0.77

 unto

0.75

wark

0.73

rative

0.72

 thereof

0.72

 reminder

0.72

Interstitial

0.70

ãĤ¢ãĥ«

0.69

Activations Density 0.320%

words related to causes and effects

relationships between symptoms and underlying causes or conditions in societal contexts

No Comments

No Known Activations