INDEX

Explanations

instances of loyalty or loyalty-related terms

oai_token-act-pair · gpt-3.5-turbo

instances of the word "loyal" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 concussion

-0.66

quick

-0.65

cloth

-0.62

annis

-0.60

phrine

-0.59

paces

-0.59

vom

-0.58

Draft

-0.58

GAME

-0.58

 Puzz

-0.57

POSITIVE LOGITS

ty

1.00

 allegiance

0.98

ties

0.96

ists

0.93

 oath

0.92

 loyal

0.88

 loyalty

0.87

alties

0.86

hips

0.86

alty

0.86

Activations Density 0.053%

instances of loyalty or loyalty-related terms

instances of the word "loyal" in various contexts

No Comments

No Known Activations