INDEX

Explanations

names of a person, potentially linked to a legal context

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Vick" and terms related to water systems

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

oric

-0.71

geist

-0.69

ppo

-0.68

 Zeit

-0.64

ãĤ¨ãĥ«

-0.64

issors

-0.62

ohydrate

-0.60

Fog

-0.60

 Catalyst

-0.60

inous

-0.60

POSITIVE LOGITS

ski

0.80

elines

0.80

 Kare

0.74

 Vick

0.73

erest

0.71

istani

0.69

pip

0.69

 Ukrain

0.68

rets

0.68

rey

0.68

Activations Density 0.035%

names of a person, potentially linked to a legal context

mentions of the name "Vick" and terms related to water systems

No Comments

No Known Activations