INDEX

Explanations

terms related to structural or functional connections, particularly in a context of anchoring or securing entities

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

RuleContext

-0.82

Capítulo

-0.77

 betweenstory

-0.75

dafx

-0.75

MMdd

-0.74

Kue

-0.70

providedIn

-0.69

gwick

-0.68

 Valeria

-0.68

billy

-0.66

POSITIVE LOGITS

 anchor

2.75

anchor

2.64

 Anchor

2.61

Anchor

2.47

 anchors

2.44

anchors

2.12

 Anch

2.08

 anchoring

2.08

 anchored

2.04

Anch

1.79

Activations Density 0.091%

terms related to structural or functional connections, particularly in a context of anchoring or securing entities

No Comments

No Known Activations