INDEX

Explanations

references to evidence and claims being substantiated in arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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



-0.88

aarrggbb

-0.73

 typelib

-0.73

 estekak

-0.70

Архівовано

-0.70

yntaxException

-0.68

MENAFN

-0.66

 IBOutlet

-0.66

קישורים

-0.63

rainian

-0.63

POSITIVE LOGITS

 evidence

0.85

evidence

0.73

 proof

0.73

 Beweis

0.65

 EVIDENCE

0.63

 bukti

0.62

 preuve

0.61

 proofs

0.61

Evidence

0.61

 corrobor

0.60

Activations Density 0.869%

references to evidence and claims being substantiated in arguments

No Comments

No Known Activations