INDEX

Explanations

instances of the word "respond" in sentences

oai_token-act-pair · gpt-3.5-turbo

instances of the word "respond" 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 @ 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

ãĥĩãĤ£

-0.81

 Marin

-0.76

 Thieves

-0.72

 Oblivion

-0.72

 Demons

-0.72

 Lions

-0.71

than

-0.68

cutting

-0.67

 Phantom

-0.66

 Blazers

-0.66

POSITIVE LOGITS

 favorably

1.05

 positively

1.00

 adequately

0.93

ivated

0.89

ively

0.87

 negatively

0.86

 appropriately

0.86

iments

0.84

 intellig

0.82

ivating

0.81

Activations Density 0.033%

instances of the word "respond" in sentences

instances of the word "respond" in various contexts

No Comments

No Known Activations