INDEX

Explanations

verbs indicating the beginning or initiation of an action or process

oai_token-act-pair · gpt-3.5-turbo

actions related to beginning or initiating activities

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

raltar

-0.79

sole

-0.74

uca

-0.72

cffff

-0.70

lette

-0.66

enthal

-0.66

 compliment

-0.64

ultimate

-0.64

liest

-0.63

xtap

-0.63

POSITIVE LOGITS

 circles

0.91

 sporadic

0.84

 patterns

0.84

 circuits

0.78

 withdrawals

0.78

 newsletters

0.77

 citations

0.75

 symptoms

0.74

 habits

0.72

 rounds

0.72

Activations Density 0.178%

verbs indicating the beginning or initiation of an action or process

actions related to beginning or initiating activities

No Comments

No Known Activations