INDEX

Explanations

verbs indicating an action being performed on something or someone

oai_token-act-pair · gpt-3.5-turbo

forms of the verb "to be" and related phrases indicating existence or presence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

é¾įå¥ĳå£«

-0.91

roo

-0.75

ģĸ

-0.73

atever

-0.71

lik

-0.67

ski

-0.67

cue

-0.66

pires

-0.66

acea

-0.64

 Thou

-0.64

POSITIVE LOGITS

 themselves

1.22

 collectively

0.87

 uniformly

0.86

 individually

0.84

 evenly

0.82

 numbered

0.81

selves

0.79

 dispersed

0.79

 varied

0.73

 scattered

0.73

Activations Density 0.569%

verbs indicating an action being performed on something or someone

forms of the verb "to be" and related phrases indicating existence or presence

No Comments

No Known Activations