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

 rendition

-0.66

 gore

-0.62

azeera

-0.61

 explorer

-0.61

 elder

-0.61

 voice

-0.61

 sounding

-0.61

MpServer

-0.60

 affair

-0.60

POSITIVE LOGITS

Rank

0.75

hid

0.72

Throw

0.69

reat

0.66

thodox

0.66

stood

0.64

erity

0.64

abad

0.64

ashion

0.64

arus

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.