INDEX

Explanations

numbers related to model names, years, or quantities

oai_token-act-pair · gpt-3.5-turbo

references to specific numerical values or identifiers

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gets

-0.90

arent

-0.81

thodox

-0.77

cha

-0.71

folk

-0.70

grass

-0.69

board

-0.68

maid

-0.67

isman

-0.67

boarding

-0.67

POSITIVE LOGITS

0.88

0.78

een

0.77

uador

0.77

0.76

0.74

0.73

Activations Density 0.058%

numbers related to model names, years, or quantities

references to specific numerical values or identifiers

No Comments

No Known Activations