INDEX

Explanations

details on activities or events involving structured procedural instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

OGND

-0.50

Kör

-0.40

 Reap

-0.39

 protoimpl

-0.39

JUR

-0.38

cifix

-0.38

WireFormatLite

-0.37

sistency

-0.37

 dove

-0.37

Cue

-0.36

POSITIVE LOGITS

 alternative

0.71

 alternatives

0.69

alternative

0.68

 alternatif

0.63

 alternativas

0.62

Alternative

0.60

 alternate

0.59

 ALTERNATIVE

0.59

 alternativa

0.59

alternatives

0.58

Activations Density 0.081%

details on activities or events involving structured procedural instructions

No Comments

No Known Activations