INDEX

Explanations

terms related to procedural steps and algorithms

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

///////////

-0.77

 Keaton

-0.73

")[

-0.71

pot

-0.70

</em>

-0.70

ة

-0.70

"=>$

-0.69

ни

-0.69

Present

-0.68

putInt

-0.66

POSITIVE LOGITS

nastics

0.97

 Algorithms

0.90

cedures

0.90

orithm

0.85

 MainAxisSize

0.85

featureID

0.84

boldsymbol

0.84

aarrggbb

0.83

 Algorithm

0.82

orithmic

0.82

Activations Density 0.156%

terms related to procedural steps and algorithms

No Comments

No Known Activations