INDEX

Explanations

the word "render" in different contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "render" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

!/

-0.72

andise

-0.70

Cly

-0.66

 Compton

-0.65

 Eisen

-0.60

swick

-0.60

bies

-0.60

 Panama

-0.60

CU

-0.60

imately

-0.59

POSITIVE LOGITS

ezvous

1.02

 obsolete

0.91

 rendered

0.87

 moot

0.84

 renders

0.82

 useless

0.81

 render

0.80

phas

0.80

 unus

0.76

rendered

0.73

Activations Density 0.051%

the word "render" in different contexts

instances of the word "render" and its variations

No Comments

No Known Activations