INDEX

Explanations

references to ambiguity and uncertainty in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ново

-0.53

tagext

-0.51

かというと

-0.47

IfNot

-0.47

 innocently

-0.46

 "'";

-0.45

 teras

-0.45

mtext

-0.44

@"/

-0.44

NIE

-0.44

POSITIVE LOGITS

 apapun

1.05

 whatever

0.99

 Whatever

0.94

 whoever

0.94

Whatever

0.93

 whichever

0.88

whatever

0.86

 Cualquier

0.81

Anything

0.80

Whoever

0.79

Activations Density 0.119%

references to ambiguity and uncertainty in various contexts

No Comments

No Known Activations