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

yet

-0.70

llan

-0.68

arios

-0.65

photo

-0.63

Requires

-0.60

 loyalty

-0.58

note

-0.57

leys

-0.57

 inher

-0.57

 purch

-0.56

POSITIVE LOGITS

rontal

0.93

emen

0.74

ãĥ¼ãĥĨãĤ£

0.70

ãĤ©

0.69

rame

0.68

ilitarian

0.68

olicy

0.66

pload

0.65

pless

0.65

 Mush

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.