INDEX

Explanations

names containing variations of 'O' followed by 'R'

oai_token-act-pair · gpt-3.5-turbo

prominent characters or titles related to specific individuals in a narrative context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ospons

-0.69

credit

-0.62

-0.61

 Ples

-0.59

 conduc

-0.58

multipl

-0.57

è£ħ

-0.57

function

-0.56

 Rohing

-0.56

ently

-0.56

POSITIVE LOGITS

inion

0.77

iverse

0.76

llor

0.75

urai

0.69

itars

0.67

 Rebellion

0.66

uliffe

0.65

 Rebels

0.65

FTWARE

0.64

raq

0.64

Activations Density 0.097%

names containing variations of 'O' followed by 'R'

prominent characters or titles related to specific individuals in a narrative context

No Comments

No Known Activations