INDEX

Explanations

phrases and words related to limitations or boundaries

oai_token-act-pair · gpt-3.5-turbo

terms related to boundaries or restrictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ublic

-0.81

rious

-0.72

nian

-0.69

TPP

-0.68

earth

-0.68

FORE

-0.67

lique

-0.67

vironment

-0.66

stown

-0.66

anka

-0.65

POSITIVE LOGITS

 limits

0.96

 imposed

0.92

 Limits

0.84

 amount

0.77

 limitation

0.75

 limit

0.74

 tolerance

0.74

 limitations

0.73

 loopholes

0.73

 restricts

0.73

Activations Density 0.030%

phrases and words related to limitations or boundaries

terms related to boundaries or restrictions

No Comments

No Known Activations