INDEX

Explanations

words related to a specific hallucinogenic substance

oai_token-act-pair · gpt-3.5-turbo

words associated with specific hallucinogenic substances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Freak

-0.72

gerald

-0.65

 dearly

-0.63

llor

-0.60

 hereafter

-0.60

<+

-0.59

FIX

-0.59

missions

-0.59

 accidents

-0.58

 glim

-0.57

POSITIVE LOGITS

steen

0.76

ipedia

0.74

umen

0.70

quez

0.70

oso

0.69

iflower

0.69

phia

0.69

ucci

0.67

agne

0.67

hurst

0.65

Activations Density 0.311%

words related to a specific hallucinogenic substance

words associated with specific hallucinogenic substances

No Comments

No Known Activations