INDEX

Explanations

mentions of people's names ending with "ent"

oai_token-act-pair · gpt-3.5-turbo

variations of the word "ent."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BILITIES

-0.80

issance

-0.67

STON

-0.67

BILITY

-0.66

side

-0.65

CTV

-0.65

iets

-0.64

TeX

-0.64

hiba

-0.63

ohn

-0.62

POSITIVE LOGITS

ropy

1.12

ucky

1.09

ertain

1.06

acles

1.03

inel

1.00

imental

0.99

ral

0.98

reprene

0.96

rification

0.96

ieth

0.91

Activations Density 0.046%

mentions of people's names ending with "ent"

variations of the word "ent."

No Comments

No Known Activations