INDEX

Explanations

references to gaps or disparities

oai_token-act-pair · gpt-3.5-turbo

references to disparities or differences across various contexts

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

ocations

-0.71

oran

-0.68

ise

-0.65

MT

-0.62

Interstitial

-0.61

istic

-0.61

abad

-0.59

ocation

-0.59

vez

-0.59

icas

-0.58

POSITIVE LOGITS

gap

1.09

 gaps

0.95

wid

0.90

 brid

0.82

Gap

0.82

locks

0.82

 widened

0.78

byss

0.78

ersed

0.77

 junction

0.76

Activations Density 0.009%

references to gaps or disparities

references to disparities or differences across various contexts

No Comments

No Known Activations