INDEX

Explanations

words related to military operations and interventions

oai_token-act-pair · gpt-3.5-turbo

references to organizational structures or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ãĥĥãĥī

-0.71

 bones

-0.66

 Territory

-0.66

ishment

-0.65

 Welsh

-0.65

agna

-0.65

 elemental

-0.62

 dstg

-0.62

 aged

-0.62

Jah

-0.61

POSITIVE LOGITS

OP

4.09

OPS

2.64

op

1.86

OPER

1.79

ops

1.76

OPE

1.73

OPA

1.64

Op

1.60

OC

1.53

OB

1.52

Activations Density 0.009%

words related to military operations and interventions

references to organizational structures or classifications

No Comments

No Known Activations