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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FK

-0.76

urat

-0.72

ipel

-0.71

RY

-0.71

ãĤ«

-0.62

cules

-0.61

PF

-0.60

ancock

-0.60

ãĤ¦

-0.58

 Dull

-0.58

POSITIVE LOGITS

ĸļ

0.90

netflix

0.80

vo

0.76

 stitching

0.73

 favour

0.70

ske

0.69

 parity

0.63

 differential

0.62

ilage

0.62

 equate

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.