INDEX

Explanations

verbs related to making adjustments or modifications

oai_token-act-pair · gpt-3.5-turbo

terms related to adjustments or modifications in data or processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

cott

-0.74

geries

-0.73

bery

-0.68

 Muse

-0.66

dest

-0.65

vas

-0.65

prom

-0.63

sic

-0.62

Prom

-0.62

itation

-0.61

POSITIVE LOGITS

 adjusted

3.62

adjusted

2.89

 Adjusted

2.62

Adjust

2.27

 adjusting

2.04

adjust

1.95

 adjust

1.88

 adjustment

1.83

 adjustments

1.74

 adjusts

1.74

Activations Density 0.009%

verbs related to making adjustments or modifications

terms related to adjustments or modifications in data or processes

No Comments

No Known Activations