INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

=]

-0.63

 ranking

-0.62

 Ranking

-0.60

ħĭ

-0.59

Ĳ

-0.57

Room

-0.57

orld

-0.56

ocide

-0.56

Ranked

-0.56

Los

-0.55

POSITIVE LOGITS

doms

0.69

argon

0.68

 Ares

0.68

vez

0.66

HG

0.62

utterstock

0.62

tis

0.61

 Jarvis

0.60

 Gillespie

0.60

 Straw

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.