INDEX

Explanations

short phrases describing relationships or connections

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases that indicate comparisons or conditions

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

":-

-0.74

ses

-0.69

ciplinary

-0.62

dim

-0.61

rite

-0.60

MpServer

-0.57

.",

-0.56

kell

-0.56

 Vaults

-0.55

erest

-0.53

POSITIVE LOGITS

 incidentally

0.89

ardless

0.89

)</

0.76

ĪĴ

0.73

arently

0.72

 spoiler

0.71

-)

0.70

udder

0.68

ãĥ©ãĥ³

0.68

theless

0.67

Activations Density 0.297%

short phrases describing relationships or connections

conjunctions and phrases that indicate comparisons or conditions

No Comments

No Known Activations