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

iqueness

-0.75

ypes

-0.75

icas

-0.72

paio

-0.72

cision

-0.71

ttes

-0.71

cffff

-0.70

zzo

-0.68

amina

-0.65

dig

-0.65

POSITIVE LOGITS

sson

0.82

volent

0.64

row

0.61

 honoured

0.60

 Sebast

0.58

ward

0.58

 Caption

0.58

 skiing

0.57

 Household

0.57

 frost

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.