INDEX

Explanations

descriptions or actions related to personal involvement or experience

oai_token-act-pair · gpt-3.5-turbo

instances of the word "personally" in reference to individual experiences or opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

iens

-0.77

 Grants

-0.74

Dispatch

-0.72

 McKin

-0.72

 Leap

-0.71

 Maid

-0.71

 Winds

-0.70

 Weaver

-0.70

 Gates

-0.70

 Mechan

-0.70

POSITIVE LOGITS

 identifiable

1.18

 personally

0.95

 speaking

0.83

 benefited

0.83

essage

0.82

 exper

0.82

 intervened

0.79

 incrim

0.79

ographed

0.79

 indul

0.78

Activations Density 0.005%

descriptions or actions related to personal involvement or experience

instances of the word "personally" in reference to individual experiences or opinions

No Comments

No Known Activations