INDEX

Explanations

phrases referring to certainty or clarity

oai_token-act-pair · gpt-3.5-turbo

declarative statements about states of being or occurrences

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

Footnote

-0.67

 audits

-0.63

itches

-0.63

stice

-0.62

erald

-0.62

DOI

-0.62

verts

-0.61

bilt

-0.61

itures

-0.60

sted

-0.60

POSITIVE LOGITS

 happening

1.35

 occurring

0.95

 transpired

0.92

 unfolding

0.88

 meant

0.86

 happ

0.86

 going

0.85

 done

0.85

 wrong

0.82

 gonna

0.81

Activations Density 0.108%

phrases referring to certainty or clarity

declarative statements about states of being or occurrences

No Comments

No Known Activations