INDEX

Explanations

words related to suppression, control, and restraint

oai_token-act-pair · gpt-3.5-turbo

instances of the word "suppress" 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 @ 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

sky

-0.73

owitz

-0.72

aldo

-0.70

member

-0.70

gain

-0.69

giving

-0.69

venture

-0.68

 Drawn

-0.67

verty

-0.66

Â¯Â¯

-0.66

POSITIVE LOGITS

ively

0.97

 suppression

0.91

 suppressing

0.86

 suppressed

0.86

 suppress

0.85

 inhib

0.79

 muzzle

0.75

 impulses

0.75

 distractions

0.74

 emotions

0.70

Activations Density 0.026%

words related to suppression, control, and restraint

instances of the word "suppress" and its variations

No Comments

No Known Activations