INDEX

Explanations

names of individuals involved in various legal or criminal activities

oai_token-act-pair · gpt-3.5-turbo

numerical information or statistics associated with individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

itionally

-0.68

ãĥ¥

-0.67

=\"

-0.67

 NETWORK

-0.65

PDATE

-0.63

natureconservancy

-0.61

Built

-0.61

entimes

-0.60

XD

-0.59

 hypothesis

-0.59

POSITIVE LOGITS

0.84

yo

0.82

0.68

 Kinnikuman

0.68

0.66

 aged

0.66

susp

0.64

0.63

Activations Density 0.152%

names of individuals involved in various legal or criminal activities

numerical information or statistics associated with individuals

No Comments

No Known Activations