INDEX

Explanations

terms related to decision-making and evaluation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ConstraintMaker

-0.61

demia

-0.59

espół

-0.58

 qualités

-0.55

vold

-0.54

 ThemeData

-0.52

 devrez

-0.52

 trattano

-0.52

 occupé

-0.52

мужские

-0.52

POSITIVE LOGITS

 Bourgoin

0.56

בח

0.54

 decipher

0.53

ρη

0.51

WriteAttribute

0.50

 prospec

0.49

 deci

0.49

données

0.47

 hierogly

0.47

 elucid

0.46

Activations Density 0.793%

terms related to decision-making and evaluation processes

No Comments

No Known Activations