INDEX

Explanations

statements involving comparisons and similarities

oai_token-act-pair · gpt-3.5-turbo

references to actions or states of being related to appearance and functionality

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

Secondly

-0.65

"},"

-0.64

rift

-0.63

iscal

-0.59

luence

-0.58

etus

-0.58

aug

-0.57

 Secondly

-0.57

iesta

-0.55

abled

-0.54

POSITIVE LOGITS

 like

2.21

 LIKE

1.89

like

1.80

 Like

1.77

Like

1.62

 akin

1.32

 alike

1.14

 analogous

1.07

 likes

1.04

 unlike

1.04

Activations Density 0.361%

statements involving comparisons and similarities

references to actions or states of being related to appearance and functionality

No Comments

No Known Activations