INDEX

Explanations

references to electrical power measurements

oai_token-act-pair · gpt-3.5-turbo

terms related to power measurements in watts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

vich

-0.79

tto

-0.76

patrick

-0.71

thia

-0.70

meat

-0.67

ptive

-0.64

 Danger

-0.63

ll

-0.63

 Currency

-0.62

 Humanity

-0.61

POSITIVE LOGITS

igans

0.88

iless

0.86

atts

0.83

aic

0.83

arios

0.83

iated

0.82

ishers

0.82

iation

0.81

orthy

0.78

 athlet

0.77

Activations Density 0.082%

references to electrical power measurements

terms related to power measurements in watts

No Comments

No Known Activations