INDEX

Explanations

references to proofs and proof-related terminology in mathematical or academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

JsonInclude

-0.90

 كومونز

-0.84

Hochspringen

-0.81

 Disqus

-0.78

 AppBundle

-0.77

 Burs

-0.77

Архівовано

-0.76

MigrationBuilder

-0.74

 Forumite

-0.73

zarchiwizowane

-0.72

POSITIVE LOGITS

Proof

2.59

 Proof

2.52

proof

2.50

 proof

2.50

 PROOF

2.31

PROOF

2.17

 proofs

2.09

 Proofs

1.88

 proofing

1.61

proofing

1.50

Activations Density 0.123%

references to proofs and proof-related terminology in mathematical or academic contexts

No Comments

No Known Activations