INDEX

Explanations

numerical values or codes

oai_token-act-pair · gpt-3.5-turbo

numerical values and codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 corrid

-0.70

phabet

-0.66

 volunt

-0.66

 nomine

-0.66

 Nass

-0.63

 compan

-0.61

 Daytona

-0.61

 Tonight

-0.61

 nailed

-0.60

 Charity

-0.59

POSITIVE LOGITS

1.14

1.13

1.12

1.10

1.08

1.07

Activations Density 0.044%

numerical values or codes

numerical values and codes

No Comments

No Known Activations