INDEX

Explanations

formal contexts or events indicated by the word "At"

oai_token-act-pair · gpt-3.5-turbo

references to specific events or meetings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 construed

-0.58

 punishable

-0.57

 favour

-0.56

 erased

-0.56

itivity

-0.56

 regretted

-0.54

SPONSORED

-0.54

isSpecialOrderable

-0.53

 proves

-0.53

 belonged

-0.53

POSITIVE LOGITS

mosp

1.35

hens

1.34

kinson

1.25

omic

1.13

 least

1.11

letico

1.08

 stake

0.95

 present

0.91

roc

0.88

kins

0.86

Activations Density 0.057%

formal contexts or events indicated by the word "At"

references to specific events or meetings

No Comments

No Known Activations