INDEX

Explanations

commonly used in the context of actions following a repeated pattern or sequence

oai_token-act-pair · gpt-3.5-turbo

repeated phrases indicating a sequence or series of events

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

ablishment

-0.74

estine

-0.72

ossier

-0.71

nai

-0.71

istan

-0.69

mie

-0.67

ittens

-0.64

erate

-0.63

zie

-0.63

roid

-0.63

POSITIVE LOGITS

encies

0.79

meal

0.67

ãĥ©ãĥ³

0.64

series

0.64

 finale

0.63

teenth

0.63

ãĥı

0.63

 engagements

0.62

ttes

0.62

 Waves

0.62

Activations Density 0.022%

commonly used in the context of actions following a repeated pattern or sequence

repeated phrases indicating a sequence or series of events

No Comments

No Known Activations