INDEX

Explanations

references to the word "trap" or related concepts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "dri" in various contexts, especially related to names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ivas

-0.86

Osw

-0.85

ikarp

-0.81

istan

-0.81

psey

-0.76

acular

-0.76

umble

-0.75

anic

-0.73

yip

-0.73

eneg

-0.72

POSITIVE LOGITS

zzy

0.78

ULTS

0.77

============

0.76

GBT

0.74

vable

0.73

zzle

0.70

abeth

0.69

zz

0.69

========

0.68

REDACTED

0.67

Activations Density 0.080%

references to the word "trap" or related concepts

occurrences of the word "dri" in various contexts, especially related to names and titles

No Comments

No Known Activations