INDEX

Explanations

names of individuals, particularly those related to sports or other fields

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Troy" and related proper nouns

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

unknown

-0.81

overs

-0.75

cffffcc

-0.73

pmwiki

-0.72

backer

-0.71

ISTER

-0.70

osures

-0.70

userc

-0.69

Ã±a

-0.67

BOOK

-0.62

POSITIVE LOGITS

 Troy

0.80

anium

0.78

anus

0.76

 Cummings

0.74

lock

0.74

master

0.73

ility

0.72

zan

0.71

 Decay

0.70

 Bram

0.70

Activations Density 0.015%

names of individuals, particularly those related to sports or other fields

occurrences of the name "Troy" and related proper nouns

No Comments

No Known Activations