INDEX

Explanations

potential scenarios or situations

oai_token-act-pair · gpt-3.5-turbo

phrases that express potential outcomes or uncertainties

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

ogie

-0.87

gar

-0.83

ging

-0.80

waters

-0.78

artney

-0.76

char

-0.75

bey

-0.73

gers

-0.73

ulu

-0.73

eye

-0.73

POSITIVE LOGITS

ossibility

0.91

llor

0.79

 horizon

0.78

 pron

0.78

 possibility

0.78

 hypot

0.74

 validity

0.73

 someday

0.73

izons

0.72

 unnecess

0.72

Activations Density 0.019%

potential scenarios or situations

phrases that express potential outcomes or uncertainties

No Comments

No Known Activations