INDEX

Explanations

phrases indicating sources of information or insider knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

AddTagHelper

-0.79

MENAFN

-0.76

UnsafeEnabled

-0.66

ButterKnife

-0.62

SequentialGroup

-0.61

ScopeManager

-0.61

SizeF

-0.61

readystatechange

-0.60

ThroughAttribute

-0.60

EndProject

-0.59

POSITIVE LOGITS

 sources

0.64

ArrowToggle

0.63

 Sources

0.63

Sources

0.57

sources

0.53

 confirmed

0.49

 confidential

0.47

 leaked

0.47

confirmed

0.47

 SOURCES

0.46

Activations Density 0.255%

phrases indicating sources of information or insider knowledge

No Comments

No Known Activations