INDEX

Explanations

phrases indicating difficulty or impossibility in achieving something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating difficulty or impossibility

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

 Accessed

-0.79

STAR

-0.77

mask

-0.73

zona

-0.68

prem

-0.66

star

-0.66

stars

-0.66

Introduced

-0.66

still

-0.63

heart

-0.62

POSITIVE LOGITS

geries

1.05

ays

0.88

 anyone

0.88

 everyone

0.86

 others

0.85

 outsiders

0.84

 oneself

0.84

 anybody

0.82

 them

0.82

bidden

0.80

Activations Density 0.094%

phrases indicating difficulty or impossibility in achieving something

phrases indicating difficulty or impossibility

No Comments

No Known Activations