INDEX

Explanations

numbers and codes

oai_token-act-pair · gpt-3.5-turbo

numerical values related to statistics or data

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

soDeliveryDate

-0.74

 simplicity

-0.66

 messenger

-0.64

arest

-0.63

 raft

-0.63

 ditch

-0.63

 misunder

-0.62

 vulner

-0.61

 sickness

-0.60

 heaviest

-0.60

POSITIVE LOGITS

0.88

0.80

0.75

0.74

0.73

 CrossRef

0.73

0.72

Activations Density 0.044%

numbers and codes

numerical values related to statistics or data

No Comments

No Known Activations