INDEX

Explanations

terms related to alignment in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

RUnlock

-0.42

'></

-0.41

HasKey

-0.41

expandindo

-0.40

ForeignKey

-0.40

 Gambia

-0.40

ConverterFactory

-0.40

cplusplus

-0.39

 gamb

-0.39

agisse

-0.39

POSITIVE LOGITS

 align

2.30

 Align

2.27

 alignment

2.27

 aligning

2.25

 ALIGN

2.20

 Alignment

2.17

align

2.13

Align

2.08

 aligned

2.08

 alignments

1.96

Activations Density 0.145%

terms related to alignment in various contexts

No Comments

No Known Activations