INDEX

Explanations

terms related to a specific topic or entity identified as "ider"

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Gazette

-0.74

 Plants

-0.69

Ã«

-0.67

 Weasley

-0.67

é¾

-0.62

estone

-0.60

Bam

-0.60

 Orwell

-0.59

Cth

-0.59

estones

-0.57

POSITIVE LOGITS

mares

0.86

berus

0.83

vous

0.78

lein

0.77

sonian

0.77

oute

0.77

ger

0.76

ied

0.75

ï¸ı

0.75

ider

0.75

Activations Density 0.043%

terms related to a specific topic or entity identified as "ider"

No Comments

No Known Activations