INDEX

Explanations

medical or technical terms related to understanding, knowledge, or consequences

oai_token-act-pair · gpt-3.5-turbo

phrases that convey the concept of understanding and its various implications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

erity

-0.81

uable

-0.79

etheus

-0.75

icides

-0.72

iaries

-0.72

odder

-0.71

ixt

-0.70

raviolet

-0.69

orthy

-0.68

umbnails

-0.68

POSITIVE LOGITS

 workings

0.89

 nuances

0.78

 Situation

0.74

 plight

0.73

WHY

0.72

 dynamics

0.72

 psychology

0.70

 reasoning

0.69

 predicament

0.69

 context

0.69

Activations Density 0.172%

medical or technical terms related to understanding, knowledge, or consequences

phrases that convey the concept of understanding and its various implications

No Comments

No Known Activations