INDEX

Explanations

mentions of local entities or activities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "local" in various contexts

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

xual

-1.03

ERSON

-0.92

hower

-0.87

issance

-0.86

haar

-0.83

_-

-0.82

ACTED

-0.81

uberty

-0.79

OHN

-0.77

vous

-0.77

POSITIVE LOGITS

ities

1.14

ised

1.06

isation

0.88

 residents

0.88

izations

0.85

 governments

0.85

 authorities

0.84

 councils

0.84

 communities

0.83

idad

0.81

Activations Density 0.027%

mentions of local entities or activities

occurrences of the term "local" in various contexts

No Comments

No Known Activations