INDEX

Explanations

terms related to tracking or monitoring processes

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

HasAnnotation

-0.97

 للمعارف

-0.95

 fermés

-0.94

 Houſe

-0.93

coltura

-0.93

########.

-0.92

 Blackman

-0.92

 duquel

-0.91

 occhiali

-0.90

 BorderRadius

-0.90

POSITIVE LOGITS

 trace

1.90

 Trace

1.80

Trace

1.71

trace

1.60

 traced

1.58

 tracing

1.54

 TRACE

1.52

 traces

1.51

TRACE

1.40

Tracing

1.35

Activations Density 0.126%

terms related to tracking or monitoring processes

No Comments

No Known Activations