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

igible

-0.69

sole

-0.65

 conspicuous

-0.61

 eyeing

-0.61

mble

-0.61

INGTON

-0.60

context

-0.60

 ironic

-0.60

idays

-0.59

generic

-0.59

POSITIVE LOGITS

Else

0.83

rene

0.79

jit

0.71

zona

0.71

Ã¡n

0.71

abies

0.67

thia

0.67

Ud

0.66

requ

0.64

obyl

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.