INDEX

Explanations

references to tribes or tribal-related terms

oai_token-act-pair · gpt-3.5-turbo

references to tribal identity and related concepts

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

mington

-0.78

————

-0.74

ablishment

-0.74

Ö¼

-0.73

gow

-0.72

ï¸

-0.71

OHN

-0.71

terday

-0.71

pread

-0.70

OPA

-0.70

POSITIVE LOGITS

 tribal

0.97

 affili

0.94

 chiefs

0.93

 tribes

0.85

 ancestry

0.83

ities

0.83

 councils

0.80

istani

0.80

 affairs

0.79

 affiliation

0.79

Activations Density 0.017%

references to tribes or tribal-related terms

references to tribal identity and related concepts

No Comments

No Known Activations