INDEX

Explanations

references to feedback and audience responses in the context of evaluations or assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

ResumeLayout

-0.57

 betweenstory

-0.55

 متعلقه

-0.52

TProtocol

-0.52

 IndexPath

-0.51

 Shakspeare

-0.50

 timeval

-0.49

StoreMessageInfo

-0.49

parsedMessage

-0.49

 invariants

-0.49

POSITIVE LOGITS

 response

1.85

 reaction

1.67

 responses

1.61

 reactions

1.59

response

1.51

 reacties

1.46

 Response

1.46

 feedback

1.43

 reception

1.41

Reactions

1.41

Activations Density 0.318%

references to feedback and audience responses in the context of evaluations or assessments

No Comments

No Known Activations