INDEX

Explanations

phrases indicating a statement or declaration being made

oai_token-act-pair · gpt-3.5-turbo

expressions of caution or reluctance to provide information

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

uses

-0.74

ngth

-0.73

itton

-0.73

ranch

-0.73

igor

-0.67

endium

-0.66

aughs

-0.66

 Juda

-0.66

pes

-0.66

fired

-0.65

POSITIVE LOGITS

 anymore

1.19

 anything

1.08

 specifics

0.93

nor

0.88

 exactly

0.84

 goodbye

0.83

 publicly

0.83

 definitively

0.81

 anybody

0.77

 anywhere

0.74

Activations Density 0.089%

phrases indicating a statement or declaration being made

expressions of caution or reluctance to provide information

No Comments

No Known Activations