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

bern

-0.92

İĭ

-0.83

romancer

-0.81

alian

-0.79

ividual

-0.74

rahim

-0.74

rises

-0.71

jobs

-0.70

site

-0.69

kefeller

-0.69

POSITIVE LOGITS

pac

0.81

 wound

0.70

 amput

0.66

 arch

0.64

Fer

0.64

di

0.64

HI

0.63

 hurd

0.63

Philipp

0.62

draft

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.