INDEX

Explanations

mentions of Italy or Italians

oai_token-act-pair · gpt-3.5-turbo

references to Italy or Italians

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

\\\\\\\\

-1.03

TPPStreamerBot

-0.88

tick

-0.88

ciating

-0.86

bilt

-0.84

lasses

-0.82

nels

-0.82

pir

-0.79

manship

-0.77

scl

-0.77

POSITIVE LOGITS

otti

0.87

etta

0.81

 Renaissance

0.81

 Fasc

0.81

zzo

0.81

 Alps

0.80

 Inquisition

0.79

 Serie

0.78

 Italy

0.77

olini

0.77

Activations Density 0.026%

mentions of Italy or Italians

references to Italy or Italians

No Comments

No Known Activations