INDEX

Explanations

phrases indicating potential outcomes or consequences of actions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating outcomes or consequences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 spaced

-0.72

 craw

-0.71

bones

-0.70

 periphery

-0.67

ut

-0.65

 Straw

-0.64

 floors

-0.64

 Secrets

-0.63

 pitch

-0.63

 vigil

-0.61

POSITIVE LOGITS

Enh

0.83

interstitial

0.80

UE

0.79

swers

0.79

uments

0.78

uced

0.78

antly

0.77

ivity

0.71

uces

0.71

enance

0.70

Activations Density 0.029%

phrases indicating potential outcomes or consequences of actions

phrases indicating outcomes or consequences

No Comments

No Known Activations