INDEX

Explanations

expressions of desire or intent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AutoScaleMode

-0.70

SourceChecksum

-0.65

OCCURRED

-0.62

 pouvant

-0.61

 étant

-0.61

 transfieras

-0.60

 AssemblyCompany

-0.60

withIdentifier

-0.58

حوالہ

-0.57

MergeFrom

-0.57

POSITIVE LOGITS

 nothing

0.88

 assurances

0.85

 assurance

0.79

 something

0.75

 reassurance

0.74

 answers

0.74

 revenge

0.74

 everyone

0.74

 desperately

0.74

 clarification

0.72

Activations Density 0.142%

expressions of desire or intent

No Comments

No Known Activations