INDEX

Explanations

phrases or words indicating the geographical or conceptual center of something

oai_token-act-pair · gpt-3.5-turbo

phrases related to centers and their significance in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ishable

-0.78

 Cosponsors

-0.71

 Fool

-0.66

osponsors

-0.65

 Emblem

-0.65

iko

-0.62

add

-0.62

keep

-0.62

 Keeper

-0.61

 pian

-0.56

POSITIVE LOGITS

 gravity

0.98

 largeDownload

0.82

rency

0.81

cipline

0.75

 Excellence

0.69

gravity

0.68

ĺħ

0.67

circle

0.66

ordinate

0.65

rovers

0.65

Activations Density 0.050%

phrases or words indicating the geographical or conceptual center of something

phrases related to centers and their significance in various contexts

No Known Activations