INDEX

Explanations

occurrences of quoted speech and references to individuals in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

TagMode

-0.75

ViewImports

-0.63

ScopeManager

-0.60

.*")]

-0.52

-0.50

="@+

-0.49

ArgsConstructor

-0.49

ftagPool

-0.49

 appelez

-0.46

GeneratedValue

-0.46

POSITIVE LOGITS

 says

2.06

 states

1.84

says

1.75

 notes

1.70

 explains

1.64

Says

1.63

 Says

1.56

 suggests

1.53

 asserts

1.44

states

1.44

Activations Density 0.792%

occurrences of quoted speech and references to individuals in a narrative context

No Comments

No Known Activations