INDEX

Explanations

prepositions followed by nouns

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "with."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

-0.91

fort

-0.75

BP

-0.70

FML

-0.68

ati

-0.68

Strange

-0.66

chuk

-0.66

unes

-0.66

]);

-0.64

cemic

-0.64

POSITIVE LOGITS

 regards

1.07

 regard

1.06

stood

1.05

draw

1.00

 apologies

0.98

drawn

0.93

 impunity

0.86

 whom

0.85

standing

0.85

 respect

0.80

Activations Density 0.084%

prepositions followed by nouns

occurrences of the word "with."

No Comments

No Known Activations