INDEX

Explanations

sections of code or technical information

oai_token-act-pair · gpt-3.5-turbo

programming-related warnings and arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

DH

-0.68

wagen

-0.66

↵Âł

-0.66

ktop

-0.65

assian

-0.62

ADV

-0.58

pmwiki

-0.57

 goat

-0.56

 Austral

-0.56

 Dane

-0.55

POSITIVE LOGITS

)</

0.81

RIP

0.77

staking

0.69

frac

0.64

NetMessage

0.60

anwhile

0.59

hibition

0.59

Uk

0.59

senal

0.59

rification

0.57

Activations Density 0.168%

sections of code or technical information

programming-related warnings and arguments

No Comments

No Known Activations