INDEX

Explanations

phrases related to a series or sequence of items

oai_token-act-pair · gpt-3.5-turbo

sequences of the word "string" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tical

-0.89

undai

-0.85

icago

-0.78

hammad

-0.77

vantage

-0.72

psy

-0.71

hyde

-0.69

mares

-0.68

roxy

-0.66

 millenn

-0.65

POSITIVE LOGITS

 bikini

0.86

entially

0.74

ify

0.74

tie

0.73

Builder

0.73

ãĤ©

0.72

ified

0.72

ãĤ¡

0.70

angled

0.70

ifying

0.70

Activations Density 0.016%

phrases related to a series or sequence of items

sequences of the word "string" in various contexts

No Comments

No Known Activations