INDEX

Explanations

terms and phrases related to actions and operational tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

✨:

-0.92

 nahilalakip

-0.88

 GenerationType

-0.86

]--;

-0.86

 Mawr

-0.82

 dermatologist

-0.78

 Kelurahan

-0.77

oughly

-0.77

theless

-0.77

 lót

-0.77

POSITIVE LOGITS

 action

1.71

 ACTION

1.70

 Action

1.69

Action

1.60

ACTION

1.56

action

1.55

getAction

1.47

IAction

1.46

 actions

1.43

Actions

1.39

Activations Density 0.063%

terms and phrases related to actions and operational tasks

No Comments

No Known Activations