INDEX

Explanations

phrases related to locations or specific elements in a narrative

oai_token-act-pair · gpt-3.5-turbo

references to the term "pulp" in various contexts, particularly related to literature or media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Aval

-0.75

 Butterfly

-0.66

rium

-0.66

ãĤ¤ãĥĪ

-0.64

 Organisation

-0.63

 Gall

-0.63

 Lennon

-0.62

 Sunshine

-0.62

 Hath

-0.62

 Defenders

-0.61

POSITIVE LOGITS

monary

1.24

pit

1.16

wark

0.99

iple

0.96

py

0.92

pees

0.89

utical

0.89

untary

0.88

leys

0.87

unte

0.87

Activations Density 0.032%

phrases related to locations or specific elements in a narrative

references to the term "pulp" in various contexts, particularly related to literature or media

No Comments

No Known Activations