INDEX

Explanations

legal and citation-related terms and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

the

-0.66

 most

-0.64

 real

-0.64

Autoritní

-0.63

حياتها

-0.61

SuccessListener

-0.60

حياته

-0.59

far

-0.59

—

-0.59

POSITIVE LOGITS

 thrombosis

0.64

 față

0.64

 hâte

0.62

 păr

0.62

 milioane

0.62

 sceptre

0.60

 BorderSide

0.60

 acidosis

0.59

 blessures

0.59

 ägg

0.58

Activations Density 0.616%

legal and citation-related terms and structures

No Comments

No Known Activations