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

ï¸

-0.94

âĨ

-0.84

ilda

-0.72

"""

-0.72

"""

-0.69

ANY

-0.65

 "$:/

-0.65

Tuc

-0.64

"],"

-0.64

âĵĺ

-0.64

POSITIVE LOGITS

²¾

0.68

 inconvenient

0.66

osi

0.65

aths

0.64

 confidential

0.64

raq

0.63

 concealed

0.63

ãĤ´ãĥ³

0.62

ewitness

0.62

 poisons

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.