INDEX

Explanations

terms related to advantages and potential or Boolean conditions in contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

rolid

-0.63

latform

-0.63

 onCancelled

-0.62

󠁢

-0.61

 dirait

-0.59

nant

-0.58

itects

-0.58

sschule

-0.57

EndGlobalSection

-0.57

 Unión

-0.56

POSITIVE LOGITS

 pros

0.93

pros

0.76

Razor

0.73

pro

0.71

 Pros

0.70

Pros

0.65

PostMapping

0.64

langsung

0.61

HttpPut

0.60

Rohy

0.59

Activations Density 0.061%

terms related to advantages and potential or Boolean conditions in contexts

No Comments

No Known Activations