INDEX

Explanations

social media actions related to blocking and unblocking users

oai_token-act-pair · gpt-3.5-turbo

terms related to blocking or unblocking, particularly in a social media or online context

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

 prest

-0.74

tti

-0.72

 subdu

-0.70

hospital

-0.70

 toget

-0.68

 mortar

-0.67

 quarters

-0.67

 composition

-0.66

 appropri

-0.66

 crest

-0.65

POSITIVE LOGITS

able

1.34

ables

1.27

ABLE

1.07

ability

1.07

ers

0.99

abilities

0.97

edIn

0.96

abled

0.95

ment

0.93

ishable

0.92

Activations Density 0.058%

social media actions related to blocking and unblocking users

terms related to blocking or unblocking, particularly in a social media or online context

No Comments

No Known Activations