INDEX

Explanations

names of people and places 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Arend

-0.74

 Charlottesville

-0.74

 Crosby

-0.71

 glycerin

-0.70

 grapefruit

-0.70

HandlerContext

-0.70

äumt

-0.69

 SpongeBob

-0.66

 hâte

-0.65

 zood

-0.65

POSITIVE LOGITS

 Swain

0.77

 Cock

0.72

Mor

0.70

Mor

0.69

kuk

0.69

endphp

0.68

 nakalista

0.67

overset

0.66

 Angus

0.66

 "../../../

0.66

Activations Density 1.972%

names of people and places in various contexts

No Comments

No Known Activations