INDEX

Explanations

references to popular movies and books

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

lington

-0.69

 alas

-0.67

ward

-0.67

INA

-0.64

ilde

-0.63

imaru

-0.63

fully

-0.63

BER

-0.62

="#

-0.61

ARA

-0.60

POSITIVE LOGITS

 apocalypse

0.84

 Ancients

0.84

 Apocalypse

0.78

 nutshell

0.77

 millennium

0.76

 Nile

0.73

 Confederacy

0.73

 beast

0.72

 Alps

0.71

 Gods

0.71

Activations Density 0.194%

references to popular movies and books

occurrences of the word "the."

No Comments

No Known Activations