INDEX

Explanations

instances where the text encourages or discourages participation in various activities

oai_token-act-pair · gpt-3.5-turbo

the phrase "participate in" across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 clocks

-0.69

 ambig

-0.68

ulence

-0.65

aeus

-0.63

 spiders

-0.63

 emerges

-0.62

 dudes

-0.62

 gears

-0.61

oxin

-0.61

 inexper

-0.61

POSITIVE LOGITS

ordinate

0.83

 conversation

0.82

 accordance

0.81

 discussions

0.79

 conversations

0.72

 Conversation

0.71

 unison

0.71

 voluntary

0.70

 daily

0.69

 Exercise

0.69

Activations Density 0.093%

instances where the text encourages or discourages participation in various activities

the phrase "participate in" across various contexts

No Comments

No Known Activations