INDEX

Explanations

words related to significant events or entities

oai_token-act-pair · gpt-3.5-turbo

the frequency of the word "major" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

tein

-0.85

 Machina

-0.76

qi

-0.71

metry

-0.71

pless

-0.69

mong

-0.68

iffe

-0.68

 Canaver

-0.67

enery

-0.67

 Leone

-0.65

POSITIVE LOGITS

 depressive

0.87

 arteries

0.83

 contributor

0.82

itarian

0.82

 league

0.77

 leagues

0.76

 artery

0.73

 chunk

0.72

 tournaments

0.72

itized

0.72

Activations Density 0.021%

words related to significant events or entities

the frequency of the word "major" in various contexts

No Comments

No Known Activations