INDEX

Explanations

code examples with commands and instructions

oai_token-act-pair · gpt-3.5-turbo

code snippets and instructions related to command-line operations or programming tasks

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 lifes

-0.75

 neighb

-0.73

 Stephenson

-0.73

 misunderstand

-0.68

 counselors

-0.67

 Rivers

-0.67

 tiss

-0.67

 tremend

-0.67

 perfected

-0.66

hement

-0.66

POSITIVE LOGITS

<?

1.32

import

1.26

$$

1.21

sudo

1.19

SELECT

1.13

CRE

1.11

mk

1.10

1.09

foo

1.06

Activations Density 0.104%

code examples with commands and instructions

code snippets and instructions related to command-line operations or programming tasks

No Comments

No Known Activations