INDEX

Explanations

words related to "mystery."

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "mystery."

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

baugh

-0.88

ibaba

-0.88

obe

-0.84

umbnail

-0.79

onest

-0.78

boa

-0.78

attery

-0.76

ocations

-0.74

ositories

-0.74

rylic

-0.74

POSITIVE LOGITS

 solved

0.89

 mystery

0.89

 mysteries

0.85

 Mystery

0.80

 unsolved

0.79

 myster

0.77

 shroud

0.76

 twist

0.76

 surrounds

0.76

 trail

0.74

Activations Density 0.016%

words related to "mystery."

references to the concept of "mystery."

No Comments

No Known Activations