INDEX

Explanations

concepts related to questions of competence and how they influence outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

protoc

-0.74

 насељу

-0.73

nodoc

-0.62

OCCURRED

-0.60

LookAnd

-0.59

InvalidProtocol

-0.56

 nhật

-0.55

RenderAtEndOf

-0.54

DECREF

-0.53

 caractéristique

-0.52

POSITIVE LOGITS

rawDesc

0.85

 handlar

0.82

={({

0.65

 darum

0.56

+"&

0.54

 ↓,

0.54

volves

0.52

 chodzi

0.52

ardin

0.52

 Symb

0.52

Activations Density 0.150%

concepts related to questions of competence and how they influence outcomes

No Comments

No Known Activations