INDEX

Explanations

programming actions or functions related to decisions and choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 ModelExpression

-0.57

brtc

-0.56

+#+#

-0.55

 contextLoads

-0.50

Interview

-0.49

ENESS

-0.48

zustellen

-0.47

맞

-0.46

 chande

-0.45

 Estimate

-0.45

POSITIVE LOGITS

 action

4.36

action

3.80

 Action

3.52

Action

3.42

 ACTION

3.33

ACTION

3.04

 acción

2.98

 actions

2.97

 ação

2.68

 azione

2.61

Activations Density 0.382%

programming actions or functions related to decisions and choices

No Comments

No Known Activations