INDEX

Explanations

mentions of the word "pin" followed by a numerical value, representing a level of interest or significance

oai_token-act-pair · gpt-3.5-turbo

references to 'Pin' or 'pin' in various contexts

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

anwhile

-0.95

ngth

-0.83

earch

-0.79

ccording

-0.78

mble

-0.78

mberg

-0.78

theless

-0.77

IGH

-0.75

 Trance

-0.74

hovah

-0.73

POSITIVE LOGITS

ning

1.06

ochet

1.05

ned

1.04

point

0.89

Pin

0.88

ball

0.88

wheel

0.86

agate

0.80

ners

0.80

nington

0.79

Activations Density 0.008%

mentions of the word "pin" followed by a numerical value, representing a level of interest or significance

references to 'Pin' or 'pin' in various contexts

No Comments

No Known Activations