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

 weekday

-0.70

 capacitor

-0.62

luc

-0.61

 endorsing

-0.61

 nonpartisan

-0.60

 strip

-0.60

 spoiler

-0.60

 ingredient

-0.59

 prestige

-0.59

 transparency

-0.58

POSITIVE LOGITS

swer

0.81

roxy

0.80

qv

0.79

sonian

0.78

doi

0.74

ieties

0.73

GG

0.73

PI

0.73

ZX

0.72

 Krug

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.