INDEX

Explanations

references to actions or functions in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

expandindo

-0.82

 démission

-0.74

̈́

-0.74

uxxxx

-0.73

$_"

-0.68

 bezig

-0.68

 tombé

-0.67

")));

-0.67

dbg

-0.66

 privée

-0.64

POSITIVE LOGITS

action

1.85

Action

1.78

 Action

1.76

ACTION

1.73

 action

1.72

 ACTION

1.62

actions

1.44

 Actions

1.37

Actions

1.35

 actions

1.22

Activations Density 0.058%

references to actions or functions in programming contexts

No Comments

No Known Activations