INDEX

Explanations

words related to locations

oai_token-act-pair · gpt-3.5-turbo

title-like phrases or names associated with creative works, events, or characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 certific

-0.74

 impair

-0.72

 eligible

-0.71

 qualifying

-0.71

 protective

-0.70

 parity

-0.69

 compliance

-0.69

 engineering

-0.68

 disapproval

-0.68

 ammon

-0.68

POSITIVE LOGITS

 Trilogy

1.37

 Principle

1.19

 Room

1.13

 Prophe

1.12

 Incident

1.11

 Boys

1.09

 Begins

1.09

 Podcast

1.08

 Collection

1.07

 Brigade

1.07

Activations Density 0.283%

words related to locations

title-like phrases or names associated with creative works, events, or characters

No Comments

No Known Activations