INDEX

Explanations

words related to submergence or immersion

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to self-reference or identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 blot

-0.73

©¶æ

-0.66

 unfinished

-0.64

 borders

-0.62

 ashes

-0.62

 limitation

-0.61

hed

-0.61

 crem

-0.60

 sidewalks

-0.60

 chopping

-0.60

POSITIVE LOGITS

oided

0.77

ocus

0.74

IAS

0.74

brew

0.74

ati

0.72

uncture

0.71

Adventure

0.70

ESSION

0.70

ONEY

0.69

LAB

0.69

Activations Density 0.418%

words related to submergence or immersion

words and phrases related to self-reference or identity

No Comments

No Known Activations