INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

puters

-0.80

flix

-0.73

Discussion

-0.67

olean

-0.63

OTOS

-0.62

puting

-0.62

 Lanc

-0.61

ONSORED

-0.61

tub

-0.60

restling

-0.59

POSITIVE LOGITS

rius

0.84

externalActionCode

0.77

actionDate

0.74

ĸļ

0.73

©¶æ¥µ

0.70

 Prophe

0.70

binding

0.69

taboola

0.67

 Cooldown

0.66

itatively

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.