INDEX

Explanations

strings of words

oai_token-act-pair · gpt-3.5-turbo

occurrences 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

undai

-0.91

tical

-0.84

hammad

-0.83

icago

-0.72

psey

-0.72

hyde

-0.71

emies

-0.70

mares

-0.69

orean

-0.68

rentice

-0.68

POSITIVE LOGITS

ãĤ¡

0.82

 bikini

0.80

ently

0.80

ency

0.76

entially

0.75

asso

0.74

angled

0.73

angle

0.73

tie

0.71

tail

0.70

Activations Density 0.016%

strings of words

occurrences of the word "string" in various contexts

No Comments

No Known Activations