INDEX

Explanations

the word "Large" followed by a number

oai_token-act-pair · gpt-3.5-turbo

references to "large" entities, groups, or scale

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

çīĪ

-0.84

gnu

-0.82

onto

-0.69

emy

-0.69

vous

-0.68

CB

-0.66

uers

-0.66

emis

-0.66

lik

-0.65

 Nich

-0.64

POSITIVE LOGITS

 sized

1.11

 intestine

1.10

 scale

1.08

 quantities

1.05

 amounts

1.01

(>

0.99

 denomination

0.92

 swat

0.88

 enough

0.88

 proport

0.85

Activations Density 0.048%

the word "Large" followed by a number

references to "large" entities, groups, or scale

No Comments

No Known Activations