INDEX

Explanations

words related to a specific person - "Kapuscinski"

oai_token-act-pair · gpt-3.5-turbo

references to the author "Kapuscinski" and related mentions 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

IBLE

-0.93

heastern

-0.82

mble

-0.76

EMENT

-0.74

nces

-0.73

mingham

-0.72

beit

-0.71

xual

-0.71

 abund

-0.70

 confir

-0.69

POSITIVE LOGITS

lar

1.03

Osw

0.87

insky

0.85

Kap

0.84

pps

0.84

usk

0.81

kat

0.79

oor

0.78

erman

0.78

ernel

0.77

Activations Density 0.031%

words related to a specific person - "Kapuscinski"

references to the author "Kapuscinski" and related mentions in various contexts

No Comments

No Known Activations