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

odon

-0.91

ICAN

-0.81

iator

-0.79

alone

-0.74

cules

-0.72

eli

-0.72

anol

-0.71

mad

-0.69

kos

-0.67

iologist

-0.67

POSITIVE LOGITS

 TAMADRA

0.67

Rated

0.65

YOU

0.63

RUN

0.63

 cycles

0.61

 Pound

0.60

Hold

0.60

ummies

0.60

ellig

0.60

Current

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.