INDEX

Explanations

metaphors within text

oai_token-act-pair · gpt-3.5-turbo

usage of metaphors and analogies in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

avorite

-0.76

ktop

-0.73

guards

-0.70

 Citiz

-0.69

ierra

-0.68

CLASSIFIED

-0.66

Assembly

-0.66

mails

-0.64

actions

-0.62

ovo

-0.62

POSITIVE LOGITS

ically

0.88

 metaphor

0.78

izon

0.76

aph

0.72

ãĤ¨ãĥ«

0.71

orical

0.70

isons

0.69

 Interpret

0.67

hetical

0.67

 metaphors

0.67

Activations Density 0.049%

metaphors within text

usage of metaphors and analogies in the text

No Comments

No Known Activations