INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

emouth

-0.72

ippi

-0.69

 narrowed

-0.68

Availability

-0.66

veyard

-0.65

onia

-0.64

fet

-0.64

 Hitman

-0.63

Gamer

-0.62

eria

-0.61

POSITIVE LOGITS

fitted

0.79

fitting

0.74

 srfAttach

0.69

mount

0.69

sod

0.68

repeat

0.66

pun

0.65

 VIDE

0.63

phasis

0.62

 Remem

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.