INDEX

Explanations

names or references to the name "Norman"

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the name "Norman."

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

Constructed

-0.85

externalActionCode

-0.84

iw

-0.81

Fra

-0.79

tnc

-0.77

favorite

-0.74

plane

-0.73

Mil

-0.73

-0.72

qua

-0.72

POSITIVE LOGITS

 Orth

0.87

 Eisen

0.87

 Cancel

0.76

 Schwarz

0.75

 Ness

0.74

oland

0.73

 Bram

0.73

 Reed

0.73

ufact

0.71

 Bates

0.70

Activations Density 0.028%

names or references to the name "Norman"

repeated mentions of the name "Norman."

No Comments

No Known Activations