INDEX

Explanations

references to authorship and contributions in research papers.

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

scientific terminology and technical data references.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

words or phrases related to present time or current status, particularly the word "Current" at the beginning of sentences.

oai_token-act-pair · claude-3-5-sonnet-20240620 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

Дереккөздер

-0.74

nezeu

-0.71

 voudrais

-0.70

 comprends

-0.69

grew

-0.68

 umano

-0.66

 AssemblyTitle

-0.64

chaun

-0.64

 remporté

-0.62

 effectually

-0.61

POSITIVE LOGITS

 affairs

0.76

 Affairs

0.66

ENSE

0.64

 generation

0.64

day

0.62

 trends

0.59

TestingModule

0.59

currentState

0.58

apiVersion

0.56

day

0.56

Activations Density 0.133%

references to authorship and contributions in research papers.

scientific terminology and technical data references.

words or phrases related to present time or current status, particularly the word "Current" at the beginning of sentences.

No Comments

No Known Activations