INDEX

Explanations

instances where a person expresses a lack of experience with something

oai_token-act-pair · gpt-3.5-turbo

expressions of personal experiences and unfamiliarity

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

-0.71

-0.66

states

-0.66

Pres

-0.65

Orig

-0.65

rays

-0.64

 Plaint

-0.64

 Progress

-0.63

redients

-0.63

 Affordable

-0.62

POSITIVE LOGITS

 encount

1.11

 heard

1.00

rontal

0.98

 experien

0.98

 personally

0.94

 wondered

0.90

 experience

0.90

 noticed

0.88

 myself

0.85

 seeing

0.84

Activations Density 0.175%

instances where a person expresses a lack of experience with something

expressions of personal experiences and unfamiliarity

No Comments

No Known Activations