INDEX

Explanations

quotes or reported speech patterns

oai_token-act-pair · gpt-3.5-turbo

phrases indicating positive or negative evaluations of situations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 whilst

-0.85

 imperialist

-0.84

 [âĢ¦]

-0.78

('

-0.74

Âł

-0.74

rael

-0.73

 neoc

-0.71

aganda

-0.69

oslov

-0.69

".[

-0.67

POSITIVE LOGITS

Adds

0.72

 hugs

0.71

CFL

0.70

 nonprofits

0.68

 Manziel

0.67

 counselors

0.67

 BART

0.67

 anecd

0.66

 Parkway

0.66

 Packers

0.65

Activations Density 1.506%

quotes or reported speech patterns

phrases indicating positive or negative evaluations of situations

No Comments

No Known Activations