INDEX

Explanations

instances where people or groups come together for a common purpose or activity

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize collective actions and collaboration

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

å£«

-0.69

 viol

-0.68

availability

-0.63

condition

-0.62

ror

-0.61

tank

-0.60

wash

-0.58

yright

-0.58

taker

-0.58

-0.56

POSITIVE LOGITS

 Together

0.87

 disparate

0.83

itud

0.77

together

0.77

 dots

0.76

yss

0.75

å¥³

0.74

 together

0.73

ãĤ¤ãĥĪ

0.73

Together

0.68

Activations Density 0.375%

instances where people or groups come together for a common purpose or activity

phrases that emphasize collective actions and collaboration

No Comments

No Known Activations