INDEX

Explanations

references to various forms of training

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 SwitchCompat

-0.70

__))

-0.60

 Keeper

-0.59

IMPORTED

-0.59

AddTagHelper

-0.58

berfläche

-0.57

примеча

-0.57

 }}"></

-0.57

GHS

-0.56

SourceChecksum

-0.56

POSITIVE LOGITS

 training

0.92

Training

0.79

training

0.75

 Training

0.74

TRAINING

0.67

 TRAINING

0.67

 pelatihan

0.65

 integrates

0.65

ConstraintMaker

0.62

 nélk

0.62

Activations Density 0.123%

references to various forms of training

No Comments

No Known Activations