INDEX

Explanations

words and phrases related to procedural guidelines or steps for tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 فريبيس

-0.98

ThroughAttribute

-0.83

NOPQRST

-0.78

GraphicsUnit

-0.78

 ब्रेकडाउन

-0.74

Bioaccumulative

-0.73

évaluateur

-0.68

GTCX

-0.68

InitVars

-0.68

 GenerationType

-0.68

POSITIVE LOGITS

 Charge

0.47

rousel

0.46

<eos>

0.45

ingh

0.45

 Charges

0.44

 intér

0.44

 charges

0.43

 till

0.43

 System

0.43

 behind

0.42

Activations Density 0.078%

words and phrases related to procedural guidelines or steps for tasks

No Comments

No Known Activations