INDEX

Explanations

No Explanations Found

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IER

-0.76

rush

-0.67

ruary

-0.62

enser

-0.62

yea

-0.61

ked

-0.60

iness

-0.60

rounder

-0.59

IUM

-0.58

ODUCT

-0.58

POSITIVE LOGITS

senal

0.82

 psychiat

0.73

ĪĴ

0.71

©¶æ

0.70

itsch

0.69

alog

0.68

icz

0.67

throw

0.66

Downloadha

0.65

dump

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.