INDEX

Explanations

phrases indicating limitations or restrictions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "limited" 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

ashington

-0.76

 Neighbor

-0.73

lyn

-0.71

Gener

-0.70

Â¯Â¯Â¯Â¯

-0.68

Mount

-0.68

PE

-0.67

tha

-0.67

[+]

-0.67

Oak

-0.66

POSITIVE LOGITS

 minded

0.87

 amounts

0.79

 collateral

0.79

 exceptions

0.78

 amount

0.77

restricted

0.77

 restricts

0.76

inous

0.76

iple

0.72

 liability

0.72

Activations Density 0.030%

phrases indicating limitations or restrictions

instances of the word "limited" in various contexts

No Comments

No Known Activations