INDEX

Explanations

phrases related to questioning or inquiry in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 barriga

-0.50

 måske

-0.47

enegal

-0.47

 chinh

-0.45

 transferência

-0.45

 funcionales

-0.43

engah

-0.42

都合

-0.42

原来

-0.41

‍♀

-0.41

POSITIVE LOGITS

 Asked

0.88

Asked

0.84

asked

0.82

DockStyle

0.79

 asked

0.78

 enquired

0.76

 queried

0.75

----</

0.75

 mergeFrom

0.75

CodedInputStream

0.74

Activations Density 0.303%

phrases related to questioning or inquiry in context

No Comments

No Known Activations