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

mosp

-0.83

*/(

-0.80

HL

-0.77

DT

-0.77

ETS

-0.75

rift

-0.75

DJ

-0.72

emouth

-0.72

DP

-0.71

hr

-0.69

POSITIVE LOGITS

 robbing

0.75

 naming

0.74

 plotting

0.69

ren

0.66

 cere

0.64

 branching

0.64

 defending

0.64

 wives

0.63

 decentral

0.62

 branding

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.