INDEX

Explanations

questions starting with "How does" and "What does"

oai_token-act-pair · gpt-3.5-turbo

questions that begin with "how does" or related phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

fights

-0.79

ascript

-0.76

devices

-0.76

isphere

-0.74

boats

-0.72

runners

-0.72

cies

-0.70

tracks

-0.70

ishly

-0.70

sers

-0.70

POSITIVE LOGITS

 anyone

0.86

 anybody

0.86

olation

0.83

olated

0.72

one

0.68

omorphic

0.67

olate

0.67

it

0.67

 this

0.67

onga

0.63

Activations Density 0.051%

questions starting with "How does" and "What does"

questions that begin with "how does" or related phrases

No Comments

No Known Activations