INDEX

Explanations

commands and code snippets related to server setup and configuration

oai_token-act-pair · gpt-3.5-turbo

programming-related symbols and terminologies, particularly for Python and database operations

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

)].

-0.82

issance

-0.78

Hes

-0.68

everal

-0.68

 afore

-0.66

 Rossi

-0.66

ierrez

-0.65

veland

-0.65

enegger

-0.64

 Canaver

-0.64

POSITIVE LOGITS

output

0.97

export

0.92

webkit

0.91

enable

0.84

shared

0.83

username

0.83

prefix

0.82

input

0.82

max

0.80

rm

0.80

Activations Density 0.047%

commands and code snippets related to server setup and configuration

programming-related symbols and terminologies, particularly for Python and database operations

No Comments

No Known Activations