INDEX

Explanations

proper nouns, specifically names like "Brian"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Brian."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

saf

-0.67

minist

-0.61

roxy

-0.58

 ranged

-0.57

 includ

-0.56

 relative

-0.56

ixed

-0.56

affe

-0.56

iction

-0.55

INS

-0.55

POSITIVE LOGITS

 Nose

0.91

 Blessed

0.85

 Fallon

0.85

 McCann

0.82

 Fitzpatrick

0.81

Moy

0.79

ne

0.79

ãĥ£

0.78

 Deer

0.78

terness

0.76

Activations Density 0.036%

proper nouns, specifically names like "Brian"

occurrences of the name "Brian."

No Comments

No Known Activations