INDEX

Explanations

verbs related to actions or events in the past that involve some form of communication or decision-making

oai_token-act-pair · gpt-3.5-turbo

end-of-text markers

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

adra

-0.76

enegger

-0.73

atever

-0.71

stood

-0.68

sit

-0.68

neath

-0.64

acebook

-0.63

farious

-0.62

omever

-0.61

ankind

-0.60

POSITIVE LOGITS

own

0.65

 aback

0.61

monton

0.59

>>

0.58

 =====

0.57

><

0.56

âĦ¢:

0.55

)]

0.55

ream

0.54

Activations Density 0.155%

verbs related to actions or events in the past that involve some form of communication or decision-making

end-of-text markers

No Comments

No Known Activations