INDEX

Explanations

code-related terms and grammar symbols such as parentheses, brackets, and equals signs

oai_token-act-pair · gpt-3.5-turbo

conditional statements and options related to choice

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

Lia

-0.52

Kah

-0.52

atorium

-0.49

mpeg

-0.49

 Marlins

-0.45

Ven

-0.45

 Sanctuary

-0.45

 Tours

-0.45

iage

-0.44

 Field

-0.44

POSITIVE LOGITS

depending

0.78

ãĤ´ãĥ³

0.61

 respectively

0.58

 undermin

0.56

 charact

0.55

 ancest

0.54

ONSORED

0.54

 explan

0.54

é¾įåĸļå£«

0.54

 challeng

0.53

Activations Density 1.799%

code-related terms and grammar symbols such as parentheses, brackets, and equals signs

conditional statements and options related to choice

No Comments

No Known Activations