INDEX

Explanations

phrases related to phrases that begin with special characters like 'âĢ'

oai_token-act-pair · gpt-3.5-turbo

occurrences of specific repeated characters or symbols

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

 Mous

-0.77

 Scarlet

-0.72

 guiActiveUnfocused

-0.71

 Manhattan

-0.71

 scattering

-0.71

 Franch

-0.69

 spiral

-0.69

 Squadron

-0.68

Roc

-0.68

 Pilgrim

-0.67

POSITIVE LOGITS

ľ

1.17

º

1.13

¬

1.07

¼

1.04

¡

1.02

¹

0.99

£

0.98

¦

0.94

Ń

0.93

°

0.91

Activations Density 0.355%

phrases related to phrases that begin with special characters like 'âĢ'

occurrences of specific repeated characters or symbols

No Comments

No Known Activations