INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Ń·

-0.79

è»

-0.78

quist

-0.76

ãĥ«

-0.75

 Surviv

-0.74

etheless

-0.72

":-

-0.68

ctors

-0.67

zl

-0.66

âĸ¬

-0.64

POSITIVE LOGITS

esters

0.77

Hub

0.75

holes

0.70

 athletics

0.69

iosity

0.64

jriwal

0.62

sterdam

0.61

addin

0.60

 athlet

0.60

 Athletics

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.