INDEX

Explanations

phrases related to the perception or interpretation of abstract concepts

oai_token-act-pair · gpt-3.5-turbo

the word "as" used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

notice

-0.74

folio

-0.74

rone

-0.73

ainer

-0.72

 COUR

-0.68

rosis

-0.66

rol

-0.66

iger

-0.65

rot

-0.63

rolet

-0.63

POSITIVE LOGITS

 well

0.96

 follows

0.94

 opposed

0.88

pired

0.88

phy

0.81

 being

0.81

 synonymous

0.80

pires

0.79

 closely

0.77

 belonging

0.76

Activations Density 0.147%

phrases related to the perception or interpretation of abstract concepts

the word "as" used in various contexts

No Comments

No Known Activations