INDEX

Explanations

code snippets and programming-related terms

oai_token-act-pair · gpt-3.5-turbo

programming-related concepts and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Singer

-0.68

 heartbeat

-0.62

 bree

-0.61

 QuÃ©

-0.61

 ribbon

-0.60

 hijacked

-0.60

 named

-0.59

rollers

-0.59

 Isabel

-0.58

 orche

-0.58

POSITIVE LOGITS

+(

1.43

1.28

+=

1.11

)+

1.10

+=

1.09

++

1.08

/(

1.07

+.

1.04

-=

1.00

Activations Density 0.069%

code snippets and programming-related terms

programming-related concepts and operations

No Comments

No Known Activations