INDEX

Explanations

references to dolls

oai_token-act-pair · gpt-3.5-turbo

mentions of dolls

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

EED

-0.81

TAIN

-0.74

ãĥ¥

-0.72

NING

-0.68

GGGGGGGG

-0.65

RAW

-0.64

riott

-0.64

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.61

 forc

-0.61

 Unified

-0.61

POSITIVE LOGITS

 doll

1.10

 dolls

1.07

maker

0.95

wright

0.87

ophone

0.82

 Doll

0.80

endor

0.78

 figur

0.77

oru

0.76

makers

0.76

Activations Density 0.019%

references to dolls

mentions of dolls

No Comments

No Known Activations