INDEX

Explanations

names or terms related to people named "Ron"

oai_token-act-pair · gpt-3.5-turbo

the word "ron" as part of various contexts, possibly relating to names or specific terms

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

tub

-0.83

 Jackets

-0.68

TPS

-0.67

PROV

-0.66

SOS

-0.66

 Norn

-0.66

urai

-0.63

 Saras

-0.62

AY

-0.61

eva

-0.60

POSITIVE LOGITS

auts

1.09

aldo

1.08

 Collider

1.05

stadt

0.97

omical

0.94

igans

0.90

ising

0.89

omics

0.88

autical

0.87

naire

0.85

Activations Density 0.028%

names or terms related to people named "Ron"

the word "ron" as part of various contexts, possibly relating to names or specific terms

No Comments

No Known Activations