INDEX

Explanations

names of individuals or entities

oai_token-act-pair · gpt-3.5-turbo

various characters, particularly those related to media and entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

AFL

-0.67

 glim

-0.61

 multiplying

-0.61

 resil

-0.61

 flares

-0.59

 magnification

-0.58

atican

-0.58

 multiply

-0.58

usterity

-0.58

Construct

-0.57

POSITIVE LOGITS

ibrary

0.99

rity

0.84

otide

0.83

steen

0.77

andra

0.76

ornia

0.75

anne

0.75

oise

0.71

ois

0.71

azar

0.71

Activations Density 0.306%

names of individuals or entities

various characters, particularly those related to media and entertainment

No Comments

No Known Activations