INDEX

Explanations

phrases indicating reasons or explanations

oai_token-act-pair · gpt-3.5-turbo

causal phrases indicating reasons or explanations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

atars

-0.68

 Travels

-0.67

haul

-0.60

://

-0.58

oided

-0.58

osite

-0.57

BILITIES

-0.57

ilated

-0.57

tid

-0.57

 bypass

-0.54

POSITIVE LOGITS

nor

1.82

 anymore

1.44

yet

1.29

nor

1.26

unless

1.16

Nor

1.04

soever

1.01

 unless

0.88

:(

0.80

 either

0.76

Activations Density 0.653%

phrases indicating reasons or explanations

causal phrases indicating reasons or explanations

No Comments

No Known Activations