INDEX

Explanations

Javascript code snippets that include a "return" statement with relatively high activation values

oai_token-act-pair · gpt-3.5-turbo

programming-related return statements in functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

vern

-0.76

andan

-0.73

hemat

-0.73

Cola

-0.72

zyme

-0.71

cream

-0.70

æĪ¦

-0.69

stem

-0.69

psey

-0.69

éĹĺ

-0.68

POSITIVE LOGITS

 Returns

1.05

 Return

0.96

Return

0.90

 TRUE

0.89

 returns

0.86

 Returning

0.81

return

0.79

 return

0.78

Returns

0.78

 NULL

0.73

Activations Density 0.012%

Javascript code snippets that include a "return" statement with relatively high activation values

programming-related return statements in functions

No Comments

No Known Activations