INDEX

Explanations

Nothing; Neuron 4 does not activate for any part of the given text, indicating it does not find what it's looking for in the provided examples

oai_token-act-pair · gpt-4-turbo

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

Roaming

-0.72

oven

-0.68

orno

-0.66

knit

-0.64

ling

-0.63

letal

-0.62

elson

-0.61

 sunscreen

-0.61

Capture

-0.61

shore

-0.61

POSITIVE LOGITS

ngth

0.73

ãĥķãĤ¡

0.70

ãĥĩãĤ£

0.69

terness

0.68

ãĥĸ

0.67

ãĥķãĤ©

0.66

 hyster

0.65

 Fortress

0.65

å¥³

0.65

ãĥĦ

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.