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

ãĤ´ãĥ³

-0.94

ifts

-0.75

ãĥķãĤ¡

-0.69

ãĤ´

-0.65

ze

-0.65

 latitude

-0.64

ãĤ¶

-0.62

 takedown

-0.62

Eid

-0.61

DEM

-0.60

POSITIVE LOGITS

artment

0.72

ersen

0.71

oir

0.71

ilon

0.71

iatrics

0.66

iston

0.66

antage

0.66

 guarant

0.65

]]

0.65

APTER

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.