INDEX

Explanations

dates and events

oai_token-act-pair · gpt-3.5-turbo

specific dates and mentions of time

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

herty

-0.77

omorphic

-0.74

keyes

-0.72

anned

-0.68

ospace

-0.68

apego

-0.67

ourge

-0.67

ilitary

-0.66

olis

-0.65

ersive

-0.64

POSITIVE LOGITS

teenth

0.93

0.85

0.84

0.81

0.79

0.78

0.77

imester

0.77

Activations Density 0.295%

dates and events

specific dates and mentions of time

No Comments

No Known Activations