INDEX

Explanations

instances of agreement or consensus

oai_token-act-pair · gpt-3.5-turbo

references to unanimous decisions or votes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rir

-0.76

neys

-0.73

nels

-0.72

idget

-0.70

nel

-0.70

lla

-0.70

stra

-0.70

href

-0.70

 Gutenberg

-0.68

 tempor

-0.67

POSITIVE LOGITS

 unanimously

1.21

 unanimous

1.14

 vote

0.85

NEC

0.84

animous

0.80

IFIED

0.80

 bipartisan

0.80

 approve

0.77

Rated

0.76

 consensus

0.76

Activations Density 0.029%

instances of agreement or consensus

references to unanimous decisions or votes

No Comments

No Known Activations