INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Ĥ¬

-0.68

NESS

-0.64

istics

-0.62

 Rouge

-0.61

)].

-0.60

 pound

-0.59

 shred

-0.59

iffs

-0.59

 html

-0.59

))

-0.58

POSITIVE LOGITS

theless

0.68

metic

0.65

reon

0.65

erg

0.62

aceae

0.61

EPA

0.61

democratic

0.61

uria

0.60

bal

0.60

ãĥĩãĤ£

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.