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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ansk

-0.74

gebra

-0.69

answer

-0.67

atoes

-0.66

nesia

-0.64

wake

-0.63

odor

-0.63

 grip

-0.62

oing

-0.62

 âĶľâĶĢâĶĢ

-0.61

POSITIVE LOGITS

SHIP

0.79

ICAL

0.77

ICS

0.76

LCS

0.74

ICLE

0.73

UGC

0.68

VS

0.67

 Marriott

0.67

HCR

0.67

earances

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.