INDEX

Explanations

The neuron is looking for occurrences of the word "thorough"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "thorough" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

CHAT

-0.72

 indirectly

-0.65

Phones

-0.64

bucks

-0.64

AMY

-0.61

AIN

-0.60

 cents

-0.60

 unilaterally

-0.59

addon

-0.59

aden

-0.59

POSITIVE LOGITS

bred

1.58

fare

1.13

going

0.98

spection

0.98

 examination

0.96

 vetting

0.90

 thorough

0.89

 examinations

0.88

 Examination

0.87

ness

0.87

Activations Density 0.043%

The neuron is looking for occurrences of the word "thorough"

occurrences of the word "thorough" and its variations

No Comments

No Known Activations