INDEX

Explanations

numerical information preceded by the word "About"

oai_token-act-pair · gpt-3.5-turbo

phrases that quantify or describe numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

CV

-0.69

Express

-0.65

nob

-0.63

ilic

-0.61

ffen

-0.60

Hol

-0.58

umbn

-0.58

ohan

-0.58

Finish

-0.57

RL

-0.57

POSITIVE LOGITS

 half

1.13

thirds

1.10

 eighty

0.97

0.93

 seventy

0.92

 dozen

0.91

0.90

half

0.90

etheless

0.89

Activations Density 0.122%

numerical information preceded by the word "About"

phrases that quantify or describe numerical data

No Comments

No Known Activations