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

aughtered

-0.88

 Skydragon

-0.84

stall

-0.70

 Guth

-0.69

 Cooperative

-0.66

 Cycle

-0.62

 Strikes

-0.61

regate

-0.61

 Modes

-0.60

worthiness

-0.60

POSITIVE LOGITS

hi

0.69

rendered

0.69

ennes

0.66

 cells

0.64

 immun

0.64

 greeting

0.62

 franc

0.62

 clergy

0.61

ayan

0.61

 sympath

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.