INDEX

Explanations

adjectives or descriptive terms related to negative experiences or conditions

oai_token-act-pair · gpt-3.5-turbo

adjectives that describe states of discomfort or issues

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

ãģ¾

-0.78

paio

-0.70

LET

-0.69

edin

-0.68

TYPE

-0.63

olson

-0.62

udeb

-0.60

antage

-0.60

 toget

-0.60

daq

-0.59

POSITIVE LOGITS

 Releases

0.94

 Solutions

0.92

 Ways

0.90

 Features

0.90

 Examples

0.90

 Removal

0.89

 Strategies

0.89

 Uses

0.87

 Improvements

0.85

 Differences

0.84

Activations Density 0.228%

adjectives or descriptive terms related to negative experiences or conditions

adjectives that describe states of discomfort or issues

No Comments

No Known Activations