INDEX

Explanations

instances where specific locations are mentioned

oai_token-act-pair · gpt-3.5-turbo

instances of the word "to" suggesting movement or purpose

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

hops

-0.70

holes

-0.63

 glances

-0.62

 packets

-0.60

awan

-0.59

 surges

-0.58

 deployments

-0.58

typ

-0.58

 vows

-0.57

uous

-0.57

POSITIVE LOGITS

 ensure

1.11

 maximize

1.07

 give

1.02

 avoid

1.01

 compensate

1.01

 accommodate

1.01

 minimize

1.00

 promote

0.98

be

0.97

 make

0.97

Activations Density 0.293%

instances where specific locations are mentioned

instances of the word "to" suggesting movement or purpose

No Comments

No Known Activations