INDEX

Explanations

words related to directions and locations

oai_token-act-pair · gpt-3.5-turbo

references to various types of locations and infrastructures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vous

-0.72

soever

-0.67

emort

-0.66

asma

-0.65

ubi

-0.65

ãģĦ

-0.63

zyk

-0.61

 spect

-0.61

 inval

-0.61

otos

-0.60

POSITIVE LOGITS

 separating

0.83

side

0.81

 divid

0.78

ilage

0.77

 entrances

0.77

pole

0.77

 Depot

0.76

iers

0.74

yards

0.73

holders

0.72

Activations Density 0.412%

words related to directions and locations

references to various types of locations and infrastructures

No Comments

No Known Activations