INDEX

Explanations

mathematical expressions or code snippets including functions or methods

oai_token-act-pair · gpt-3.5-turbo

programming-related syntax and structure

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

catentry

-0.64

-0.61

 Entered

-0.61

EMA

-0.54

.</

-0.54

}.

-0.52

>[

-0.52

.''

-0.52

''.

-0.52

©¶æ¥µ

-0.51

POSITIVE LOGITS

oaded

0.65

ogether

0.63

versions

0.62

earch

0.59

endum

0.59

afety

0.58

mma

0.58

urations

0.56

 itself

0.56

ngth

0.56

Activations Density 1.568%

mathematical expressions or code snippets including functions or methods

programming-related syntax and structure

No Comments

No Known Activations