INDEX

Explanations

domain-specific terms related to datasets

oai_token-act-pair · gpt-3.5-turbo

references to datasets and their methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

touch

-0.69

idan

-0.67

 signs

-0.67

secut

-0.66

ode

-0.65

otic

-0.65

odes

-0.65

erd

-0.63

woods

-0.63

inence

-0.63

POSITIVE LOGITS

 dataset

0.95

 datasets

0.85

ĸļ

0.75

 Beir

0.74

ãĤ¼ãĤ¦ãĤ¹

0.73

0.68

hemer

0.67

 Lans

0.67

ngth

0.66

 GOODMAN

0.66

Activations Density 0.018%

domain-specific terms related to datasets

references to datasets and their methodologies

No Comments

No Known Activations