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

 Skydragon

-0.85

entimes

-0.77

 toget

-0.74

 liqu

-0.71

-0.70

bia

-0.69

 Petro

-0.67

ipedia

-0.66

yip

-0.65

)</

-0.64

POSITIVE LOGITS

 iteration

0.69

 Gould

0.68

Bun

0.61

steps

0.61

Pt

0.61

 Grassley

0.60

 closest

0.59

later

0.59

wal

0.58

:=

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.