INDEX

Explanations

mentions of names that start with "Ke" followed by a variety of letters

oai_token-act-pair · gpt-3.5-turbo

occurrences of specific names or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Flavoring

-0.80

channelAvailability

-0.74

ashtra

-0.73

catentry

-0.68

 illeg

-0.66

 smuggled

-0.63

 DRAG

-0.60

 specificity

-0.60

 Lucius

-0.60

SHIP

-0.60

POSITIVE LOGITS

bye

0.78

aston

0.77

chuk

0.75

pie

0.74

ury

0.72

warm

0.71

lein

0.70

lyn

0.69

uke

0.68

kens

0.67

Activations Density 0.060%

mentions of names that start with "Ke" followed by a variety of letters

occurrences of specific names or identifiers

No Comments

No Known Activations