INDEX

Explanations

names of people and their positions in a list or group

oai_token-act-pair · gpt-3.5-turbo

references to individuals and their actions or roles within a context

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

SON

-0.68

ynchron

-0.67

Constructed

-0.64

bees

-0.63

Built

-0.63

Token

-0.63

native

-0.62

cms

-0.61

Soft

-0.61

ifi

-0.61

POSITIVE LOGITS

 photographed

0.85

 flanked

0.84

 portraits

0.83

 pictured

0.83

OTOS

0.74

 Courtesy

0.73

 IMAGES

0.73

Jaw

0.71

 labelled

0.71

 photographs

0.71

Activations Density 0.084%

names of people and their positions in a list or group

references to individuals and their actions or roles within a context

No Comments

No Known Activations