INDEX

Explanations

references to a specific name, "Nicoli", and its variations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "oli" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

*/(

-0.85

eer

-0.81

 Cosponsors

-0.81

rants

-0.75

spin

-0.74

 Agents

-0.74

lied

-0.72

worthiness

-0.72

IAL

-0.71

dash

-0.68

POSITIVE LOGITS

oli

1.17

ague

1.04

zzo

0.96

ppe

0.90

oti

0.88

Ã¨re

0.84

ipop

0.84

ugi

0.83

omon

0.83

aea

0.81

Activations Density 0.006%

references to a specific name, "Nicoli", and its variations

occurrences of the word "oli" in various contexts

No Comments

No Known Activations