INDEX

Explanations

words or sequences containing "gn"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "gnostic" and its variations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

WHERE

-0.79

Materials

-0.74

 Gamble

-0.73

PRES

-0.71

LIST

-0.69

MER

-0.69

media

-0.69

Grant

-0.69

âĹ¼

-0.68

fitting

-0.68

POSITIVE LOGITS

ostic

1.07

osis

0.98

ostics

0.93

agons

0.93

gn

0.92

omon

0.91

acles

0.91

gling

0.91

ome

0.90

ogly

0.88

Activations Density 0.011%

words or sequences containing "gn"

occurrences of the term "gnostic" and its variations

No Comments

No Known Activations