INDEX

Explanations

names or terms related to people

oai_token-act-pair · gpt-3.5-turbo

instances of names and terms related to "Lac" and "McL."

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

ãģ®éŃĶ

-0.85

 Tens

-0.73

æĢ

-0.72

ħĭ

-0.71

CRIP

-0.71

ãĥīãĥ©

-0.70

BILITY

-0.69

BIP

-0.69

UCT

-0.69

FORE

-0.66

POSITIVE LOGITS

rosse

0.97

azy

0.89

ritch

0.79

intosh

0.78

opa

0.78

ert

0.78

mark

0.78

court

0.77

fed

0.76

anchester

0.73

Activations Density 0.047%

names or terms related to people

instances of names and terms related to "Lac" and "McL."

No Comments

No Known Activations