INDEX

Explanations

words related to changes or modifications to something

oai_token-act-pair · gpt-3.5-turbo

concepts related to major changes or modifications in systems, particularly in legislation or regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

adding

-0.61

Wee

-0.61

USE

-0.60

Bone

-0.58

 Corpus

-0.58

Na

-0.57

 presses

-0.56

 calf

-0.55

 foam

-0.55

 Grac

-0.54

POSITIVE LOGITS

1.06

sonian

0.99

sie

0.95

ed

0.83

schild

0.78

ing

0.77

sers

0.77

ership

0.77

ysis

0.74

ski

0.73

Activations Density 0.059%

words related to changes or modifications to something

concepts related to major changes or modifications in systems, particularly in legislation or regulations

No Comments

No Known Activations