INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

estyles

-0.82

 Flavoring

-0.77

-0.74

 Dame

-0.72

 contrace

-0.71

omore

-0.71

 Plays

-0.69

 reperto

-0.69

 reconc

-0.68

ereo

-0.68

POSITIVE LOGITS

bes

0.71

gear

0.70

lan

0.69

gart

0.66

kes

0.62

ne

0.61

gel

0.61

gn

0.61

gas

0.60

oros

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.