INDEX

Explanations

terms related to "desperation" or "imperative."

oai_token-act-pair · gpt-3.5-turbo

repeated uses of the term "per."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ategory

-0.73

ADRA

-0.72

ichick

-0.69

erald

-0.68

osp

-0.67

rained

-0.67

ESCO

-0.66

krit

-0.66

OME

-0.64

alions

-0.64

POSITIVE LOGITS

manent

0.98

cussion

0.96

monkey

0.93

due

0.93

ceptions

0.82

taining

0.80

formed

0.78

secution

0.77

intendent

0.76

vasive

0.75

Activations Density 0.016%

terms related to "desperation" or "imperative."

repeated uses of the term "per."

No Comments

No Known Activations