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

irie

-0.66

cffff

-0.66

NetMessage

-0.65

ridges

-0.64

 mammal

-0.62

licts

-0.61

cest

-0.60

lict

-0.60

edia

-0.60

gins

-0.60

POSITIVE LOGITS

Adv

0.72

ovsky

0.71

USB

0.71

Hamilton

0.69

Peg

0.69

 Dash

0.67

ossal

0.67

Dash

0.66

GPU

0.65

alon

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.