INDEX

Explanations

mentions of knowledge and understanding in various contexts

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

 GONNA

-0.71

 calyx

-0.70

 sinner

-0.69

 comisión

-0.66

 Oester

-0.66

 dictadura

-0.65

 depolar

-0.63

 Curran

-0.63

 Comisión

-0.62

 Burrell

-0.62

POSITIVE LOGITS

 knowledge

1.58

 Knowledge

1.45

knowledge

1.45

Knowledge

1.42

 KNOWLEDGE

1.17

NOWLEDGE

1.16

 knowled

1.10

 conocimientos

0.97

ledge

0.96

 propOrder

0.93

Activations Density 0.051%

mentions of knowledge and understanding in various contexts

No Comments

No Known Activations