INDEX

Explanations

expressions of uncertainty or doubt

oai_token-act-pair · gpt-3.5-turbo

expressions of uncertainty

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

ufact

-0.93

gencies

-0.77

perty

-0.76

iets

-0.76

gdala

-0.75

agents

-0.73

irrel

-0.71

Ĥİ

-0.70

incial

-0.70

atial

-0.70

POSITIVE LOGITS

 enough

0.89

 Dragonbound

0.76

how

0.73

 anymore

0.73

yet

0.72

why

0.70

terday

0.70

 about

0.66

 footing

0.61

 Dying

0.60

Activations Density 0.016%

expressions of uncertainty or doubt

expressions of uncertainty

No Comments

No Known Activations