INDEX

Explanations

expressions of uncertainty or doubt

oai_token-act-pair · gpt-3.5-turbo

expressions of uncertainty or doubt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ufact

-0.90

iets

-0.82

gdala

-0.80

gencies

-0.74

irrel

-0.70

asus

-0.69

HEAD

-0.69

rup

-0.68

attery

-0.68

%]

-0.67

POSITIVE LOGITS

 enough

0.85

 anymore

0.80

 Dragonbound

0.76

yet

0.73

terday

0.71

how

0.68

 Dying

0.62

ifiable

0.62

heon

0.61

 footing

0.61

Activations Density 0.017%

expressions of uncertainty or doubt

expressions of uncertainty or doubt

No Comments

No Known Activations