INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

andem

-0.68

 tandem

-0.68

RL

-0.65

 weap

-0.64

mt

-0.62

 chromos

-0.62

 arrang

-0.62

 inference

-0.61

 contingency

-0.61

 cryst

-0.60

POSITIVE LOGITS

ipedia

0.77

aban

0.76

lÃ©

0.76

arantine

0.75

uria

0.75

netflix

0.74

Story

0.74

adesh

0.73

cers

0.73

ication

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.