INDEX

Explanations

instances of the word "for" at the end of sentences

oai_token-act-pair · gpt-3.5-turbo

phrases indicating something is being sought after

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

mort

-0.72

founded

-0.69

roach

-0.68

alone

-0.68

SourceFile

-0.67

edition

-0.67

section

-0.67

oller

-0.66

 Democr

-0.65

operated

-0.65

POSITIVE LOGITS

 clues

0.92

WARD

0.91

 opportunities

0.80

bidden

0.79

omething

0.78

 alternatives

0.77

 ways

0.75

gotten

0.75

 forgiveness

0.75

 loopholes

0.74

Activations Density 0.041%

instances of the word "for" at the end of sentences

phrases indicating something is being sought after

No Comments

No Known Activations