INDEX

Explanations

sentences ending with either a period or a specific symbol

oai_token-act-pair · gpt-3.5-turbo

sentences that express strong negative sentiments or highlight distressing situations

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

ilibrium

-0.77

 organis

-0.76

omics

-0.74

 envis

-0.72

itably

-0.71

 compositions

-0.69

ikuman

-0.69

 conceptual

-0.69

 grouping

-0.69

 computing

-0.67

POSITIVE LOGITS

 Their

1.05

 They

1.05

 Says

0.96

 Meanwhile

0.95

 Residents

0.94

 Shame

0.90

 Families

0.90

 Parents

0.89

 Pict

0.86

 Especially

0.85

Activations Density 0.979%

sentences ending with either a period or a specific symbol

sentences that express strong negative sentiments or highlight distressing situations

No Comments

No Known Activations