INDEX

Explanations

references to actions and activities within a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

✨:

-1.10

 nahilalakip

-0.97

 GenerationType

-0.96

 Púb

-0.92

 universitarios

-0.89

 للاسماء

-0.88

theless

-0.88

SequentialGroup

-0.86

 Kelurahan

-0.85

 Putih

-0.84

POSITIVE LOGITS

 action

2.22

 Action

2.15

 ACTION

2.05

Action

2.05

action

1.96

ACTION

1.86

 actions

1.84

 Actions

1.74

Actions

1.73

actions

1.66

Activations Density 0.055%

references to actions and activities within a technical context

No Comments

No Known Activations

references to actions and activities within a technical context

No Comments

No Known Activations