INDEX

Explanations

directional terms, such as 'left' and 'right'

oai_token-act-pair · gpt-3.5-turbo

directional language and phrases related to advantages and disadvantages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 DRAG

-0.72

 Ging

-0.69

 "$:/

-0.67

 Exhibit

-0.62

 veto

-0.59

 CODE

-0.59

 Orders

-0.59

sbm

-0.59

 Deal

-0.58

 Trend

-0.58

POSITIVE LOGITS

 extent

1.15

venge

1.02

 detriment

0.92

livion

0.76

 heights

0.76

 tune

0.75

 fullest

0.74

ulkan

0.74

 lengths

0.73

rouse

0.69

Activations Density 0.234%

directional terms, such as 'left' and 'right'

directional language and phrases related to advantages and disadvantages

No Comments

No Known Activations