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

ted

-0.94

alogy

-0.89

alogue

-0.79

azeera

-0.74

Discover

-0.72

TING

-0.72

sing

-0.72

ksh

-0.72

igate

-0.71

ritch

-0.71

POSITIVE LOGITS

 conditional

0.65

 Revised

0.65

 disposed

0.64

 Hier

0.63

 poles

0.62

um

0.62

 Dynamics

0.61

Hav

0.61

 tentative

0.58

 vitri

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.