INDEX

Explanations

phrases indicating ability or possibility

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Reloaded

-0.65

Lug

-0.61

erville

-0.60

NetMessage

-0.56

abin

-0.56

hess

-0.55

REF

-0.54

atti

-0.54

alloc

-0.53

entin

-0.53

POSITIVE LOGITS

 guessed

1.04

 attest

0.90

 imagine

0.88

 guess

0.82

 infer

0.81

seen

0.77

 doubtless

0.73

see

0.73

 noticing

0.72

 notice

0.72

Activations Density 0.041%

phrases indicating ability or possibility

No Comments

No Known Activations