INDEX

Explanations

keywords related to past statistics or events

oai_token-act-pair · gpt-3.5-turbo

phrases that reference recent seasons or time periods in sports contexts

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

oola

-0.83

aband

-0.74

cil

-0.72

ansk

-0.70

erning

-0.68

ilateral

-0.68

kaya

-0.67

rite

-0.67

obs

-0.67

ordes

-0.65

POSITIVE LOGITS

 ditch

1.04

 week

0.98

 month

0.93

 year

0.91

 season

0.87

 minute

0.85

 semester

0.78

decade

0.78

 outing

0.78

 night

0.77

Activations Density 0.061%

keywords related to past statistics or events

phrases that reference recent seasons or time periods in sports contexts

No Comments

No Known Activations