INDEX

Explanations

words related to the current or present state of something

oai_token-act-pair · gpt-3.5-turbo

references to the current state of affairs or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wright

-0.90

aths

-0.80

later

-0.77

kick

-0.76

another

-0.76

alties

-0.75

fing

-0.74

formerly

-0.74

lehem

-0.74

olean

-0.74

POSITIVE LOGITS

 incarnation

1.28

 iteration

1.24

 spate

1.15

 predicament

1.14

 situation

1.10

 crop

1.07

 edition

1.06

 occupant

1.05

 generation

1.03

 version

0.92

Activations Density 0.061%

words related to the current or present state of something

references to the current state of affairs or situations

No Comments

No Known Activations